TextGGUF2024–2026
Sarvam AI · India
Indian models focused on 22 languages of India. Sarvam 30B and 105B (2026) are MoE models with strong reasoning and agent skills. In November Sarvam-Prism came out (Apache 2.0, based on Sarvam-105B): a decision model that, given a context and questions with fixed answer options, returns the probability of each in one pass and writes no text. It needs a graphics card with FP8 and about 120 GB of memory (B200 or H200); a paid API exists too.
- Multilingual customer support
- Reasoning and calculation tasks
- Agents with tool calling
- Sizes
- 2B – 105B-A10B
- Hardware
- from: Laptop
TextOllama2024–2026
NVIDIA · USA
NVIDIA models for agents and reasoning, optimized to run fast on its GPUs. Nemotron 3 is a Mamba and MoE hybrid from 4B to 550B; Nano Omni handles video, audio and images (English only). The new Nemotron 3.5 Super VL (120B, 12B active, up to 1M-token context) reads text, images and video up to two minutes, with a focus on documents and agents; the compressed Bolt (74B, 9B active) fits into 24 GB of video memory. Super VL languages: English, Spanish, French, German, Italian, Japanese. Dory 1.0 (4B, up to 256K-token context, English) runs the same block of layers several times, and the number of passes can be changed per task: more passes give more accuracy without a new model and without long reasoning in the text.
- Agents with tool calling
- Reasoning and calculation tasks
- Answers based on long documents
- Sizes
- 4B – 550B-A55B
- Hardware
- from: Laptop
Speech to textRU2023–2026
NVIDIA · USA
Fast NVIDIA speech recognition models, including streaming ones for real-time use. Parakeet TDT v3 and Nemotron 3.5 ASR understand Russian. The new Nemotron 3.5 Transcribe (34B, 4.3B active, OpenMDW 1.1) transcribes recordings of up to an hour in 40 languages, translates speech, splits it by speaker, puts word timestamps and answers questions about the content (questions in English only); all tasks are available for Russian. Ready files only, live streaming is not supported. The figures are the authors: 5.33% word errors on English in the open Hugging Face leaderboard.
- Transcribing calls and meetings
- Video subtitles
- Real-time voice input
- Sizes
- 110M – 34B-A4.3B
- Hardware
- from: Laptop
Text2025–2026
Ant Group (inclusionAI) · China
An Ant Group family: Ling for standard models, Ring for reasoning ones. There are trillion-parameter flagships and the efficient Ling-3.0-tiny, which needs only 1.3 billion active parameters. The new Ling-3.1-flash (560B, 25B active, 1M-token context) targets agents, office tasks and development. The improved Ling-3.1-flash-1019 (MIT) raised the Artificial Analysis index from 41 to 44 by the authors estimate.
- Corporate assistant
- Agents for office processes
- Financial analytics (Fin version available)
- Sizes
- 7.9B-A1.3B – 1T
- Hardware
- from: Laptop
Text analysisRU2026
Liquid AI · USA
Small decision models: from text, an image or a voice clip they answer yes or no, pick an option or give a rating in one pass, without writing text. d1-3B sees images, d1-omni-600M also hears speech up to 30 seconds. Russian is listed. The open d1-2B (text, pictures and video, based on LFM3-VL-2B) and d1-Omni-2B (sound as well) decide in milliseconds, 5.7 ms on an H100 by the authors measurements; besides choosing an answer they pull out text, numbers and dates with their positions and find objects in a picture. It is not a chat model.
- routing requests and tickets to teams
- checking a photo for defects or violations against a list of questions
- routing voice commands
- Sizes
- 600M, 2B and 3B
- Hardware
- from: Laptop
TextRUOllama2025–2026
Liquid AI · USA
Models with a new architecture for on-device use: fast on a regular CPU and on phones. Versions for data extraction, RAG and tools, plus LFM2.5-VL for images and voice LFM2.5-Audio. The largest, LFM2.5-24B-A2B (2.45B active, 131K-token context, Russian in the language list), always reasons before answering and targets fast on-device agents. In October the LFM3 generation came out on a new tri-hybrid architecture: LFM3-1.7B for local agents (256 thousand tokens of context, about 1 GB of memory at 4 bits, pre-trained on 22 trillion tokens), LFM3-VL-2B for images, LFM3-Audio-2B for speech and LFM3-Omni-2B, which understands text, images, video and sound and answers in text and speech. The authors do not recommend it for complex code and multi-step reasoning.
- Offline assistant on a laptop or phone
- Data extraction from documents
- Tool calling in apps
- Sizes
- 230M – 24B-A2B
- Hardware
- from: Laptop
Documents and OCROllama2026
OpenBMB (ModelBest) · China
The first MiniCPM model built only for documents: it reads text, tables, formulas, charts and seals, and pulls the needed fields out of papers. Just 1.3B. By the authors' tests, 93.68 on Real5-OmniDocBench (document parsing in real conditions: scans, photos, skewed and recaptured pages) and 54.7 on OCRBench v2. Chinese and English are stated, Russian is not. An auxiliary DSpark model is published for it that speeds up generation: according to the authors processing is 55% faster, and the speed is about 1.5 times that of PaddleOCR-VL-1.6 and 3.6 times that of MinerU2.5 Pro. It runs in vLLM, SGLang, llama.cpp and Ollama, with compressed GGUF, AWQ and GPTQ versions.
- parsing scans and photos of documents into markup: text, tables, formulas
- extracting fields from invoices, contracts and forms in Chinese and English
- fast processing of a document flow on a small server
- Sizes
- 1.3B
- Hardware
- from: Laptop
Computer-use agentsGGUF2025–2026
Ant Group (inclusionAI) · China
An Ant Group family for finding elements on screen and completing tasks in phone and computer interfaces. UI-Venus-2 was specifically trained to refuse dangerous actions. In October LBS-27B came out (Apache 2.0, based on Qwen3.8-27B): it learns to pick and zoom into the needed parts of an image on interface markup, and carries this skill over to ordinary questions about pictures.
- Automating actions in mobile apps
- Filling in forms in web interfaces
- UI autotests
- Sizes
- 2B – 72B
- Hardware
- from: Laptop
Text analysisRU2026
vLLM Semantic Router project · international project
An open family of models for an AI gateway: they answer a request with probabilities without generating text. They detect topic and urgency, jailbreak attempts, harmful requests, personal data and whether a tool is needed. Small versions run on a CPU, Vela understands 17 languages including Russian. The new d3 (27B) also reads several images and videos, and d3-turbo is, by the authors' own estimate, 4 points more accurate on text. The newest in the line, d3-ultra, came out on October 24.
- routing requests between models and teams
- checking a request for a jailbreak attempt or harmful content before the main model
- finding personal data with positions in a text
- Sizes
- 0.3B – 27B
- Hardware
- from: Laptop
Search and RAGRU2025–2026
NVIDIA · USA
NVIDIA embeddings for search and RAG. Nemotron-3-Embed, released in 2026, is under the permissive OpenMDW license and works in many languages. In October Nemotron-3.5-Embed (1B and 8B, OpenMDW 1.1) came out: it finds documents by text and by the image of a page with tables, charts and infographics; for text it was tested in 34 languages, Russian among them. The 8B is built on Ministral 3.
- Search across corporate documents
- RAG for chatbots and assistants
- Search across images and pages (VL versions)
- Sizes
- 1B – 8B
- Hardware
- from: Laptop
Text2026
jialinyyzz (sgaofen) · not stated
A 12B model that rewrites drafts written by AI so that they read like a person wrote them: emails, essays, reports, forum posts. It is trained to keep every number, unit, date, name and quote and to add nothing. It runs on your own computer; there is a ready app for Mac and Windows that works offline, and GGUF files of different compression for llama.cpp. Stated languages: English and Chinese, Russian is not stated. By the author's measurements, the Originality.ai detector judged 95% of the English rewrites human. The result still has to be read through, especially numbers and names.
- rewriting drafts of emails and reports so that they sound more natural
- editing texts after AI without losing numbers, dates and quotes
- local processing of texts that must not be sent to the cloud
- Sizes
- 12B
- Hardware
- from: Laptop
Documents and OCRRU2026
Datalab · USA
A tiny OCR model that runs on an ordinary CPU with no graphics card and no PyTorch: it uses ONNX Runtime, takes about 230 ms per page on four cores and reads up to 49 pages per second. It turns PDFs and images into markdown, plain text or JSON with boxes for lines and blocks (headings, lists, tables, captions) and reading order. In digital PDFs it takes the existing text layer and recognises only what is missing. Russian is among the stated languages. For handwriting, formulas and complex tables the authors point to their larger Chandra. The speed and accuracy figures are the authors' own.
- fast bulk conversion of PDFs and scans to markdown on a server with no graphics card
- search over document archives: text with boxes and reading order
- pre-marking pages before a heavy model
- Sizes
- about 1M parameters (the models weigh about 18 MB)
- Hardware
- from: Laptop
Forecasting2026
Mistral AI · France
A family of models for forecasting time series with no task-specific training: from the history of sales, demand or load it gives a forecast with intervals (21 quantiles). It takes up to 32 thousand points of history and forecasts up to 1024 steps at a time. By Mistral's measurements, the best zero-shot model on GIFT-Eval, TIME and fev-bench. Runs on a CPU.
- forecasting sales and demand from history
- forecasting load on a warehouse, a till, a call center
- assessing the risk of stock shortage or surplus from forecast intervals
- Sizes
- 5M, 28M, 123M and 209M
- Hardware
- from: Laptop
Text analysis2026
Mistral AI · France
Quickly identifies the language and dialect of text in Arabic script: Modern Standard Arabic, all dialects and 51 classes overall. It tells apart close languages in the same script (Persian, Urdu, Pashto and others) so that a text is not called Arabic just because of its letters. Runs on a CPU.
- detecting the dialect in customer requests in Arabic
- sorting texts by language in Arabic script
- preparing data for training and search
- Sizes
- a fastText model with calibration, parameter count not stated
- Hardware
- from: Laptop
Medicine2026
MIT CSAIL, Massachusetts General Hospital and Harvard Medical School · USA
Finds 60 anatomical structures on an X-ray: ribs, vertebrae, pelvis and limb bones. They can be used to measure, for example, the curvature angle of the spine automatically. It does not look for pathologies and does not tell right from left.
- labeling anatomy on X-ray images
- measuring the spine curvature angle
- matching fluoroscopy frames with CT for navigation
- Sizes
- a small U-Net, 256 by 256 pixel images
- Hardware
- from: Laptop
Speech to text2026
Cactus Compute · not stated
Speech recognition in a single 16.9 MB file: runs on a phone, watch, robot and CPU without a graphics card. Languages: English, German, French, Spanish, Italian, Dutch, Polish. Gives word timestamps.
- voice input in mobile apps without internet
- controlling a device by voice
- highlighting words in subtitles by timestamps
- Sizes
- 16.9 MB
- Hardware
- from: Laptop
Speech to textRUGGUF2025–2026
Mistral AI · France
Mistral's speech models: they understand audio, transcribe and answer questions about a recording. The Realtime version recognizes speech live and supports Russian; speech synthesis and a separate version for Arabic dialects are also available.
- Transcribing and summarizing recordings
- Asking questions about audio
- Real-time recognition
- Sizes
- 3B – 24B
- Hardware
- from: Laptop
Text analysis2026
Supersonic Labs · not stated
A very small decision model: from a text, a question and answer options it picks one option, gives a rating or answers yes or no. Runs on an ordinary CPU and in the browser.
- routing requests by topic
- detecting the tone of reviews
- fast classification of requests
- Sizes
- 144M
- Hardware
- from: Laptop
Speech to text2026
Fermion Research · not stated
A very compact English speech recognition model: 164 MB, close in accuracy to its large Parakeet base. Transcribes an hour of audio in about 20 seconds on a laptop.
- transcribing English meetings and calls
- dictating text on a laptop offline
- subtitles for English videos
- Sizes
- 164 MB (about 2.1 bits per weight)
- Hardware
- from: Laptop
Search and RAGOllama2025–2026
Google · USA
Small multilingual embeddings from Google that run on a phone or laptop without internet. The second version also understands images, video and audio in one vector space.
- On-device document search
- RAG without sending data outside
- Search over photos, video and audio by a text query
- Sizes
- 300M и 740M (EmbeddingGemma 2)
- Hardware
- from: Laptop
Documents and OCRGGUF2025–2026
LightOn · France
A French OCR model that converts a page into text in one pass and is fast on high volumes. The third generation (0.8B, 1B, 4B) also returns block coordinates, image descriptions and chart data as a table. Languages on the version 2 card: European languages, Chinese and Japanese; no Russian.
- Recognising invoices and contracts in European languages
- Table recognition
- Converting PDFs to text for search and RAG
- Sizes
- 0.8B – 4B
- Hardware
- from: Laptop
Image + textOllama2024–2026
OpenBMB (ModelBest and Tsinghua University) · China
Compact vision models that run even on a phone or laptop. Good at reading text in photos and understanding video; version 4.6 is only 1.3B. The fresh 4.7 comes in two sizes, 1B and 35B-A3B, the first MoE model in the family. According to the authors, 35B-A3B runs on an iPhone 17 Pro Max at 13+ tokens per second with 3 GB of memory thanks to their way of loading experts. The figures come from the authors themselves.
- On-device text recognition in photos
- Processing receipts and documents without sending them to the cloud
- Describing photos and video
- Sizes
- 1B – 35B-A3B
- Hardware
- from: Laptop
TextRU2025–2026
AI Laboratory of the North-Eastern Federal University · Russia
The most complete set of models for the Sakha (Yakut) language in one place: language models of several sizes, translation to and from Russian, embeddings and text recognition from images. Quality varies, so test it on your own data.
- Answering and writing in the Sakha language
- Translating documents and materials
- Semantic search over Sakha texts
- Sizes
- 1.1B – 27B
- Hardware
- from: Laptop
TextRUOllama2024–2026
Cohere Labs · Canada
Multilingual models from Cohere's research arm, covering 23 to 100+ languages. Tiny Aya (2026, 3.3B) runs on a regular PC, but for non-commercial use only.
- Translation and correspondence in less common languages
- Multilingual chat assistant
- Analysis of images with text (Vision)
- Sizes
- 3.3B – 35B
- Hardware
- from: Laptop
Text analysisRU2026
Tvoy_Tezka (failed09) · not disclosed
A small toolkit for Bashkir text: a fill-mask language model, a Bashkir language detector, fastText embeddings, a Bashkir-Russian pair scorer and a letter restorer. All published in autumn 2026, so check quality on your own data.
- Spellchecking and word suggestion in Bashkir
- Separating Bashkir texts from other languages
- Restoring language-specific letters in text
- Sizes
- 50M for BashkirRoBERTa
- Hardware
- from: Laptop
Plates and vehicles2020–2026
Mikel Brostrom (open project) · not disclosed
A set of trackers: it links the same vehicle across frames and cameras, which is how flow and time on site are counted. Filming vehicles and people and storing the records is personal data processing: agree the procedure with a lawyer.
- Counting vehicles crossing a line
- Following a vehicle across frames
- Finding the same vehicle on another camera
- Sizes
- trackers plus re-identification models from compact to large
- Hardware
- from: Laptop
Text analysis2026
FlowX.AI · USA and Romania
A family of small models that pull amounts, deal parties, jurisdictions, accounts and sanctions-screening mentions out of banking and insurance texts. A human makes the decision on a disputed operation; automatic blocking without review is not acceptable.
- Extracting amounts, parties and jurisdictions from operation descriptions
- Parsing customer due diligence material and sanctions lists
- Marking account numbers and payment details in documents
- Sizes
- about 150M (based on ModernBERT-base)
- Hardware
- from: Laptop
Text analysisGGUF2026
FlowX.AI · USA and Romania
Small models from a banking software company that read the text of an SMS, email or chat message and explain which scam tactic it uses. A human makes the decision on a disputed operation; automatic blocking without review is not acceptable.
- Flagging incoming messages that show signs of deception
- Explaining which phrase triggered the flag
- Filtering emails and messages before they reach an operator
- Sizes
- 0.6B – 1.7B
- Hardware
- from: Laptop
TextRU2024–2026
Sber · Russia
Sber open models with strong Russian language support and local context, from 10B-A1.8B to 702B, all MIT. GigaChat3.1-Audio handles recordings up to two hours; GFusion is a fast diffusion text version.
- Russian-language employee assistant on your own server
- Customer replies and request handling in Russian
- Working with contracts and internal policies
- Sizes
- 10B-A1.8B – 702B-A36B
- Hardware
- from: Laptop
Text analysis2024–2026
Urchade Zaratiana and Fastino AI · France / USA
Finds the entities you need in text without training: just list what to look for (name, amount, date). GLiNER2 also classifies text. Multilingual versions understand Russian.
- Extracting names, amounts and dates from emails and contracts
- Parsing requests into CRM fields
- Classifying requests by topic
- Sizes
- about 50M to 500M
- Hardware
- from: Laptop
Drawings and CADRUGGUF2026
GreenMap · not disclosed
A set of small models for Russian-language construction drawings: it finds the drawing area, title block and legend, marks up walls and hatching, and pulls sheet data into JSON along with references to standards. A draft that an engineer checks.
- Finding the title block, legend and drawing area on a sheet
- Marking up walls and hatching on a floor plan
- Extracting drawing data into structured JSON
- Sizes
- 3.5M - 4B
- Hardware
- from: Laptop
Faces2021–2026
InsightFace (deepinsight) · China
The most widely used open toolkit for face detection and recognition. Many identity-preserving image generators are built on it. The pretrained weights are non-commercial.
- Detecting and comparing faces in photos
- Face-based access in prototypes
- Face processing as part of other AI systems
- Sizes
- packages from 16 MB to 407 MB
- Hardware
- from: Laptop
Plates and vehicles2026
Intel · USA
Intel models for vehicle video analytics: car, truck, bus, motorcycle, plus entry and exit logging and vehicles stopped too long. Filming vehicles and people is personal data processing: agree the procedure with a lawyer.
- Counting vehicles and splitting them by type
- Logging vehicle entry and exit
- Monitoring parking space occupancy
- Sizes
- YOLO26 variants from nano to x
- Hardware
- from: Laptop
TextOllama2023–2026
Shanghai AI Laboratory · China
Models from Shanghai AI Laboratory. The early InternLM line is general-purpose; the new Intern-S1/S2 is scientific: it understands formulas, molecules, charts and images.
- Research assistant: papers, formulas, data
- Analysis of scientific and technical documents
- Corporate chat on small models
- Sizes
- 1.8B – about 1T
- Hardware
- from: Laptop
Text2024–2026
MBZUAI, Institute of Foundation Models (IFM, LLM360 project) · UAE
Fully open models from the UAE: data, training code and intermediate checkpoints are published along with the weights. K2-Horizon (2026) spans 0.9B to 375B with context up to 512K tokens.
- Reasoning, maths and technical questions
- Analysing long documents
- Agents and writing code
- Sizes
- 0.9B – 375B-A23B
- Hardware
- from: Laptop
Tabular data2025–2026
Stable AI (Beijing, with Tsinghua University) · China
A table model that alone can classify, predict numbers and fill in missing data. The lightweight LimiX-2M runs on an ordinary computer.
- Filling gaps in 1C and CRM exports
- Churn prediction and scoring
- Classifying customers and products
- Sizes
- 2M – 16M and LimiX-2
- Hardware
- from: Laptop
CodeGGUF2025–2026
JetBrains · Czech Republic
JetBrains models for fast code autocompletion. Mellum2 (12B, 2.5B active) is already a full assistant: it writes and edits code, calls tools and reasons. Version 2.1 spent most of its training on reinforcement learning in real repositories with a shell and tests: 47 on SWE-bench Verified, self-reported by JetBrains.
- Fast code autocompletion on your own server
- A developer assistant that does not send code to the cloud
- Fine-tuning on the company's code
- Sizes
- 4B – 12B-A2.5B
- Hardware
- from: Laptop
Music and soundGGUF2022–2026
m-a-p (Multimodal Art Projection) · UK / China
A music encoder: turns a track into a numeric representation used to detect genre, mood, key and rhythm. MERT-v2 handles full songs up to 6 minutes.
- Automatic tagging of a music catalog
- Finding similar tracks
- Detecting genre, mood and tempo
- Sizes
- 95M – 632M
- Hardware
- from: Laptop
Text2024–2026
OpenBMB (ModelBest and Tsinghua University) · China
Compact text models that run directly on a device: laptop, phone or mini PC. The 1B and 2B MiniCPM5 models focus on tool calling and long context.
- A local chat assistant without the cloud
- Data extraction and text classification
- Tool calling and simple agents on low-end hardware
- Sizes
- 0.5B – 8B
- Hardware
- from: Laptop
Tabular data2025–2026
Amazon (AutoGluon team) · USA
Amazon's tabular model built into AutoGluon: classification and regression from examples with brief fine-tuning. Mitra-v2 handles more rows and columns.
- Predicting churn and repeat purchases
- Scoring applications
- Predicting deal or order value
- Sizes
- about 76M
- Hardware
- from: Laptop
Voice: speakers and soundGGUF2026
NVIDIA · USA
Marks up a recording by speaker: who spoke when, for up to eight participants, both in files and live. The model is small, ships a GGUF build and runs without a GPU. Call recordings are personal data, so retention rules are agreed with a lawyer.
- Splitting a call or meeting recording by participant
- Adding speaker names to a transcript
- Live speaker labelling during a conversation
- Sizes
- 100M
- Hardware
- from: Laptop
Search and RAGGGUF2026
Perplexity · USA
Embeddings from the Perplexity search service. Some versions take into account the context of the whole document, not just a single fragment.
- Search across large document collections
- RAG that accounts for document context
- Website and catalog search
- Sizes
- 0.6B – 9B
- Hardware
- from: Laptop
Voice assistants2026
Samsung · South Korea
Tiny audio-understanding models for smartphones: they listen to speech, music and ambient sounds and answer in text - describing a recording and answering questions about it. They run on the device itself; prompts and answers are in English - no other languages are present in the training data.
- Describing an audio recording in words
- Answering questions about a sound
- Identifying the type of sound and the setting
- Sizes
- 99M – 356M
- Hardware
- from: Laptop
Tabular data2025–2026
Layer 6 AI (TD Bank) · Canada
A tabular model from a Canadian bank's AI lab, trained on real tables rather than only synthetic ones. Version 1.2 Turbo made computation orders of magnitude faster.
- Scoring applications and customers
- Predicting churn
- Classifying transactions and customers
- Sizes
- about 60–80M
- Hardware
- from: Laptop
Tabular data2022–2026
Prior Labs (University of Freiburg) · Germany
A ready-made model for tables: it takes example rows and immediately predicts for new ones, without lengthy training or tuning. Only v2 is free for business; newer versions are non-commercial.
- Predicting customer churn from a CRM export
- Scoring applications and leads
- Classifying customers from 1C data
- Sizes
- from a few to hundreds of millions of parameters
- Hardware
- from: Laptop
Deepfake detection2023–2026
Adobe Research and University of Surrey · USA
An image watermark for arbitrary resolutions built for the Content Authenticity Initiative: it can both apply a mark and remove one. The detector errs in both directions - a human reviews the output.
- Marking images on the way out of your own pipeline
- Checking the provenance of a submitted image
- Linking with content provenance metadata
- Sizes
- model types Q and P with different mark capacity
- Hardware
- from: Laptop
TranslationRUGGUF2026
Mergen Kungaa · not disclosed
Russian to Tuvan translation that runs on your own machine: ready GGUF builds, a LoRA adapter and a standalone Windows app. The author warns that names, numbers and important text should be double-checked with a native speaker.
- Translating documents and notices into Tuvan
- Translating Tuvan texts into Russian
- Draft translation without sending data outside
- Sizes
- 4B and 12B
- Hardware
- from: Laptop
Acoustic monitoring2019–2026
Google · USA
A tiny model covering 521 sound events, including alarms, breaking glass and screams: it fits on a microcontroller and runs without a GPU. A microphone can capture people voices, which is personal data, so check the procedure with a lawyer.
- Fast sound labelling right on the device
- Detecting alarm sounds on a site
- Picking interesting fragments out of a continuous recording
- Sizes
- 3.7M
- Hardware
- from: Laptop
Finance2024–2026
MaLA Lab, Singapore Management University (with University of Technology Sydney) · Singapore
A pretrained model that finds anomalous nodes in a relationship graph and marks suspicious vertices on a new graph without training on it. A human makes the decision on a disputed operation; automatic blocking without review is not acceptable.
- Finding suspicious accounts and counterparties linked to each other
- Highlighting atypical participants in a payment graph
- Testing hypotheses about ring schemes and chains of intermediaries
- Sizes
- weights file about 1.5 MB
- Hardware
- from: Laptop
Drawings and CAD2026
FusionBrain Lab, Lomonosov Moscow State University and Innopolis University · Russia
It writes CadQuery code from images and a point cloud, then edits its own output over several rounds, comparing the resulting shape with the original. This is a draft model: an engineer checks and signs off the document.
- Recovering a parametric model from photos and a scan of a part
- Step-by-step refinement of a draft CAD model
- Digitising parts that have no drawings
- Sizes
- 2.2B
- Hardware
- from: Laptop
TextRUOllama2024–2026
Cohere · Canada
Business models: document search with source citations, tool calling, many languages. Command A+ (2026) was the first under Apache 2.0, followed by the North line: code, translation and compact vision.
- Knowledge-base answers with source citations
- Agents that work with internal systems
- Translation and correspondence in different languages
- Sizes
- 2.5B – 218B-A25B
- Hardware
- from: Laptop
Deepfake detection2025–2026
University of Michigan · USA
A lightweight detector of generated images, trained on 2.7M samples from nearly 5000 different generators. It errs in both directions: the result is a reason for a human to check, not proof.
- Checking submitted photos and illustrations
- Filtering AI images in a content flow
- Flagging suspicious images for manual review
- Sizes
- 22M
- Hardware
- from: Laptop
Search and RAGRU2024–2026
Sber (SberDevices) · Russia
Sber embeddings built for Russian: according to the developers, among the best on Russian-language search benchmarks. FRIDA is compact, Giga-Embeddings is more powerful.
- Search across Russian-language documents
- RAG for chatbots in Russian
- Classifying requests and reviews
- Sizes
- 480M – 10B-A1.8B
- Hardware
- from: Laptop
TextOllama2023–2026
Zhipu AI (Z.ai) · China
One of the oldest Chinese open lines: from ChatGLM-6B to GLM-5.3. Strong at agentic tasks and programming; GLM-5.3-Flash understands images and is released under MIT.
- Corporate chat assistant
- Agents for routine office tasks
- Help for developers
- Sizes
- 1.5B – 744B-A40B
- Hardware
- from: Laptop
Speech to textGGUF2025–2026
IBM · USA
IBM speech models for recognizing and translating speech in English, several European languages and Japanese. Designed for enterprise use.
- Transcribing business meetings
- Translating speech into text in another language
- Voice assistants
- Sizes
- 470M – 8B
- Hardware
- from: Laptop
Text2024–2026
Tencent · China
Tencent language models: from small 0.5B–7B to Hy4-preview with 770 billion parameters. Since 2026 the line has been renamed Hy, and new versions are released under Apache 2.0.
- Corporate assistant
- Translation and multilingual texts
- Agents with tools
- Sizes
- 0.5B – 770B-A49B
- Hardware
- from: Laptop
TextOllama2024–2026
IBM · USA
IBM enterprise models with transparent training data and ISO 42001 certification. Granite 4 is a memory-efficient Mamba and Transformer hybrid.
- Answers based on internal documents (RAG)
- Tool calling and agent work
- Data extraction and classification
- Sizes
- 350M – 34B
- Hardware
- from: Laptop
Acoustic monitoring2021–2026
MLCommons · USA
A reference autoencoder for finding anomalies in machine sound: it learns only from recordings of a healthy unit and flags deviations. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.
- Listening to a machine tool, pump or conveyor
- Flagging deviations from a unit usual noise
- Training on your own recordings of healthy equipment
- Sizes
- a tiny fully connected autoencoder sized for microcontrollers
- Hardware
- from: Laptop
Computer vision2024–2026
Microsoft Research · USA
Reconstructs the 3D geometry of a scene from one photo: depth in meters, a point cloud and surface normals.
- Measuring rooms and objects from photos
- 3D point cloud from a single shot
- Preparing data for robots and AR
- Sizes
- ViT-S – ViT-G
- Hardware
- from: Laptop
Speech to textGGUF2024–2026
Moonshine AI (Useful Sensors) · USA
Very small and fast speech recognition models for phones, tablets and embedded devices. Version 2 streams, producing text while the person is still speaking.
- Voice control of devices
- Offline recognition on a phone
- Live subtitles
- Sizes
- 27M – 245M
- Hardware
- from: Laptop
TextRUOllama2023–2026
Alibaba · China
A family of language models with strong Russian language support, from small versions for a laptop to a flagship on par with commercial APIs.
- Chatbot and knowledge-base assistant
- Replies to emails and customer requests
- Document parsing and classification
- Sizes
- 0,6B – 2,4T-A95B
- Hardware
- from: Laptop
Documents and OCR2026
TeleAI (China Telecom) · China
A new lightweight document parsing model that led the OmniDocBench v1.6 benchmark at release. Handles pages photographed on a phone and crumpled pages well. Languages on the card: Chinese, English, Japanese.
- Recognising invoices and delivery notes photographed on a phone
- Recognising tables and formulas
- Converting documents to Markdown for RAG
- Sizes
- about 1.2B
- Hardware
- from: Laptop
Forecasting2024–2026
Google · USA
A ready-made Google forecasting model: forecasts any time series without training on your data.
- Sales and demand forecasting
- Purchase and inventory planning
- Load and traffic forecasting
- Sizes
- 200M – 500M
- Hardware
- from: Laptop
Deepfake detection2023–2026
University of Wisconsin-Madison · USA
An early and still used approach: a simple classifier trained on top of a frozen CLIP that transfers to unseen generators. It errs in both directions - the output needs a human check.
- Checking images from new, unfamiliar generators
- A baseline when comparing detectors
- Fast rollout of a check without training a large model
- Sizes
- a linear classifier on top of CLIP ViT-L/14
- Hardware
- from: Laptop
Voice: speakers and sound2022–2026
Community: Ultimate Vocal Remover (Anjok07), ZFTurbo, MVSep · International community
A large open collection of models for separating vocals from music and noise: MDX-Net, BS-RoFormer, Mel-RoFormer, SCNet. The quality leaders for vocals among open solutions.
- Clean vocals from a recording with music
- Backing tracks and stems for karaoke
- Removing background music and noise from videos
- Sizes
- from tens to hundreds of millions of parameters
- Hardware
- from: Laptop
Speech to textRU2022–2026
Aigiz Kunafin (AigizK), member of the SLONE community · Russia
Years of work by one enthusiast around the Bashkir Common Voice project: Whisper, wav2vec2, w2v-BERT and GigaAM fine-tuned for Bashkir, Tatar and Mari. Quality differs between models, so test them on your own recordings.
- Transcribing calls and meetings in Bashkir and Tatar
- Subtitles for video and radio broadcasts
- Turning archive recordings into text
- Sizes
- from 220M to 1B across the different models
- Hardware
- from: Laptop
TextRUGGUF2025–2026
Swiss AI (ETH Zurich, EPFL, CSCS) · Switzerland
Switzerland's public open model: weights, data and recipe are open, with more than 1000 languages in training. Version 1.5 understands images.
- Multilingual assistant
- Answers based on documents
- Analysis of images and scans (v1.5)
- Sizes
- 0.5B – 70B
- Hardware
- from: Laptop
Acoustic monitoring2023–2026
Cornell Lab of Ornithology and Chemnitz University of Technology · USA and Germany
Recognition of more than 6000 bird species by voice, the baseline tool for acoustic monitoring of an area. A microphone on site also records people voices, which is personal data, so check the procedure with a lawyer.
- Long-term monitoring of the sound background of a site
- Assessing biodiversity for an environmental review
- Selecting events from round-the-clock recordings
- Sizes
- a compact EfficientNet-B0 based model
- Hardware
- from: Laptop
Voice: speakers and sound2022–2026
Meta AI, then Alexandre Défossez · France
A classic model that splits a track into vocals, drums, bass and the rest. The v4 hybrid transformer version remains the benchmark; the project is now maintained by its author in his own repository.
- Separating vocals from music in a recording
- Backing tracks and karaoke stems
- Cleaning speech in videos with background music
- Sizes
- tens of millions of parameters
- Hardware
- from: Laptop
TextOllama2024–2026
LG AI Research · South Korea
Korean-English models from LG. Most of the line is non-commercial, but the flagship K-EXAONE 2.0 with 750 billion parameters is released under Apache 2.0.
- Corporate assistant
- Working with Korean and English texts
- Analysis of documents and images (4.5)
- Sizes
- 1.2B – 750B-A37B
- Hardware
- from: Laptop
Tabular data2026
LG AI Research · South Korea
LG's small tabular model: with 21M parameters it nearly matches the leaders in classification and regression accuracy. Weights are for non-commercial use only.
- Pilot churn forecasts
- Testing scoring hypotheses
- Exploring customer data
- Sizes
- about 21M
- Hardware
- from: Laptop
Speech to textRUGGUF2024–2026
Sber · Russia
Sber's models for Russian speech recognition, among the most accurate for Russian. Includes emotion recognition, v3 with punctuation, and a multilingual version (Russian, Kazakh, Kyrgyz, Uzbek).
- Transcribing calls in Russian
- Meeting minutes
- Voice control of services
- Sizes
- 220M – 600M
- Hardware
- from: Laptop
RerankersGGUF2024–2026
Jina AI · Germany
Strong multilingual rerankers; m0 also ranks pages as images (scans, slides). The latest versions are open for non-commercial use only.
- Refining search results before a chatbot answers
- Sorting retrieved PDF pages and slides
- Catalog and knowledge base search
- Sizes
- 33M – 2.4B
- Hardware
- from: Laptop
TextGGUF2025–2026
Kakao · South Korea
Compact Korean-English models from Kakao. Kanana 2 30B-A3B is fast thanks to MoE; small 1–3B versions suit a regular PC.
- Support chatbot
- Customer request classification
- Lightweight assistant on your own PC
- Sizes
- 1.3B – 30B-A3B
- Hardware
- from: Laptop
TextRUOllama2023–2026
Mistral AI · France
European models focused on speed. Mixtral was one of the first open mixture-of-experts models; there are versions for images (Pixtral, Medium 3.5), Lean proofs and moderation (Shieldstral).
- Fast chat responses
- Data extraction from text
- Translation and multilingual work
- Sizes
- 3B – 675B
- Hardware
- from: Laptop
RecommendersGGUF2025–2026
Kuaishou · China
An open foundation model for recommendations from a short-video service: browsing and purchase history is fed to the model as a sequence and it predicts the next item or clip. Fine-tuning on your own data is required.
- A personal feed of products or content
- Picking the next item from order history
- Recommendations inside ad slots
- Sizes
- 1.7B, 8B
- Hardware
- from: Laptop
Plates and vehicles2024–2026
ankandrew (open project) · not disclosed
Ready-made ONNX detectors that find the license plate in a frame, plus general object detectors. Filming vehicles and people and storing the records is personal data processing: agree the procedure with a lawyer.
- Finding the plate in a camera frame
- Preparing a crop for character reading
- Picking frames with vehicles out of a video stream
- Sizes
- YOLO-v9 detectors at input sizes from 256 to 640 pixels
- Hardware
- from: Laptop
Image + textGGUF2024–2026
Alibaba (AIDC-AI) · China
Vision models from Alibaba's international division with strong text and table reading. The line includes the Ovis2.6 MoE and separate compact OvisOCR models for documents.
- Extracting data from invoices, contracts and delivery notes
- Table recognition
- Answering questions about photos and charts
- Sizes
- 0.9B – 80B-A3B
- Hardware
- from: Laptop
Rerankers2026
Tencent · China
A pair of small Tencent models based on Qwen3 that pick the right skill for an AI agent for a given request: the embedding model finds candidates, the reranker chooses the best one.
- Choosing a tool or skill for an AI agent
- Routing requests between bot scenarios
- Search across a catalog of internal tools
- Sizes
- 0.6B
- Hardware
- from: Laptop
Voice: speakers and sound2023–2026
RVC-Project community · China
The most widely used open voice conversion tool: a model for a specific voice trains on 10–30 minutes of recording and works in real time. Use only with the voice owner's consent.
- Voicing content with one brand voice
- Covers and vocal work
- Real-time voice changing
- Sizes
- tens of millions of parameters
- Hardware
- from: Laptop
TranslationRU2022–2026
SLONE (David Dale, Aigiz Kunafin and others) · not disclosed
A community that extends NLLB and mBART to low-resource languages. Its models cover Erzya, Tuvan, Bashkir, Tatar, Chuvash, Buryat, Mari, Khakas and Karachay-Balkar. Quality differs by language, so test it on your own texts.
- Translating from Russian into a national language and back
- Preparing bilingual materials and signage
- Aligning parallel texts
- Sizes
- 42M for the compact encoders, 620M – 758M for the translators
- Hardware
- from: Laptop
Documents and OCRRU2024–2026
Datalab · USA
A compact OCR toolkit from the makers of Marker and Chandra: text recognition, page layout, reading order and tables. Surya OCR 2 (650M) also runs on a CPU, and Russian is among the supported languages.
- Recognizing scans and PDFs, including in Russian
- Page layout: headings, tables, images, reading order
- Recognizing tables by rows and columns
- Sizes
- up to 650M
- Hardware
- from: Laptop
Voice: speakers and soundGGUF2022–2026
WeNet community · China
A set of ready-made voiceprint models: checks whether the same person speaks in two recordings and helps split a recording by speaker. One of the models is built into pyannote 3.x.
- Voice verification of a customer during a call
- Finding repeat calls from the same person
- Splitting a recording by speaker
- Sizes
- from a few to tens of millions of parameters
- Hardware
- from: Laptop
Satellite and geo2025–2026
Allen Institute for AI (Ai2) · USA
Ai2's family of models for Sentinel-1, Sentinel-2 and Landsat imagery, with ready-made fine-tunes for mangroves, deforestation and ecosystem types. The license excludes the extractive industries.
- Monitoring deforestation and forest condition across the supply chain
- Classifying land and crops from image series
- Image embeddings for finding similar plots
- Sizes
- Nano – Large (Base about 114M)
- Hardware
- from: Laptop
TextOllama2024–2026
Google · USA
Compact Google models that run well on a single computer; larger versions understand images. Includes CodeGemma for code, FunctionGemma 270M for function calling and the fast DiffusionGemma.
- Offline assistant on a laptop
- Reading photos of documents and receipts
- Customer request classification
- Sizes
- 270M – 31B
- Hardware
- from: Laptop
Moderation and safety2024–2026
GLiNER community (Fastino, Knowledgator, NVIDIA and others) · USA
Small GLiNER-based models for finding personal data: passports, phone numbers, accounts, addresses. Data types are set in words. Russian is not officially supported.
- Masking personal data before cloud AI
- Finding passport data and bank details in documents
- Checking data exports for leaks
- Sizes
- about 200M to 500M
- Hardware
- from: Laptop
Image + textOllama2024–2026
Moondream (M87 Labs) · USA
A small, fast vision model for product use cases: answering questions, finding and pointing to objects, captions. Moondream 3.1 is a 9B MoE with 2B active.
- Finding and counting objects in photos
- Checking photos from field reports
- Captions and tags for a catalogue
- Sizes
- 2B – 9B-A2B
- Hardware
- from: Laptop
Math and reasoningOllama2025–2026
Open Thoughts (Stanford, Berkeley and other universities) · USA
Fully open reasoning models: both weights and training data are published. Newer OpenThinkerAgent versions can carry out multi-step tasks.
- Calculations and formula checks
- Complex analytics with step-by-step breakdowns
- Checking the logic of internal policies
- Sizes
- 1.5B – 32B
- Hardware
- from: Laptop
Acoustic monitoring2019–2026
University of Surrey · UK
The classic set of convolutional networks that label sound across the 527 AudioSet categories, from machinery noise and alarms to breaking glass and screams. The system does not make a diagnosis, it gives you a reason to check the unit before it fails. A microphone can also capture people voices, which is personal data, so check the procedure with a lawyer.
- Labelling what is happening in a microphone recording
- Detecting alarms, breaking glass, screams
- A base for your own model tuned to one shop floor
- Sizes
- from 5.9M (CNN6) to 81.9M (CNN14)
- Hardware
- from: Laptop
Documents and OCRRU2022–2026
Baidu (PaddlePaddle) · China
Classic lightweight PaddleOCR models: detecting and recognizing lines of text plus page layout. They run on CPUs and phones; there is a separate model for East Slavic languages, including Russian.
- Recognizing text on scans, photos and screens
- Reading labels, displays and markings in production and warehouses
- Page layout: tables, formulas, stamps, headings
- Sizes
- from 1.5M to tens of millions of parameters
- Hardware
- from: Laptop
Speech to textRUGGUF2026
Alibaba (Qwen) · China
Speech recognition models from the Qwen team for 50+ languages, including Russian. They handle noise, singing and accents well.
- Transcribing calls and meetings
- Video subtitles
- Multilingual recognition
- Sizes
- 0.6B – 1.7B
- Hardware
- from: Laptop
Computer vision2025–2026
Roboflow · USA
Real-time object detector, an open alternative to YOLO without AGPL. Supports segmentation (object outlines) and, since 2026, keypoints.
- Object detection in video and photos
- Precise outlines of parts and defects
- Fine-tuning for your own object classes
- Sizes
- Nano – 2XL
- Hardware
- from: Laptop
Forecasting2025–2026
NXAI · Austria
A compact forecasting model on the xLSTM architecture, a leader in open benchmarks despite its small size. Runs fast on a regular CPU.
- Demand and sales forecasting
- Energy consumption forecasting
- Forecasts on modest hardware and on site
- Sizes
- about 35M to 82M
- Hardware
- from: Laptop
Moderation and safety2024–2026
NVIDIA · USA
NVIDIA content filters for bots, with separate models for keeping the conversation on topic and detecting jailbreaks. Safety Guard v3 was trained on 9 languages; Russian was tested only without fine-tuning.
- Checking bot requests and replies
- Keeping the bot within its topic
- Detecting attempts to bypass rules
- Sizes
- 4B – 8B
- Hardware
- from: Laptop
Photo editing2023–2026
BRIA AI · Israel
BRIA's background removal, trained on licensed photos. Soft edges, hair, transparency. Video versions available. Business use requires a paid agreement.
- Cutting products out onto a white background
- Staff and expert photos without background
- Background removal in video
- Sizes
- 44M – 220M
- Hardware
- from: Laptop
Text to speechRUGGUF2025–2026
Resemble AI · USA
Speech synthesis with voice cloning and adjustable expressiveness. The multilingual version supports 23 languages, including Russian; Turbo and Flash are sped up for live dialogue.
- Voice for a bot or assistant
- Cloning a brand voice
- Voicing videos
- Sizes
- about 350M – 500M
- Hardware
- from: Laptop
TextRUOllama2023–2026
Cognitive Computations (Eric Hartford) · USA
Uncensored fine-tunes of Llama, Mistral, Qwen and others that fulfill almost any request. Filtering and moderation are fully on the deployer; do not show it to customers without your own filter.
- Assistant that does not refuse legal but sensitive topics
- Internal tools under a strict system prompt
- Role-play and creative scenarios
- Sizes
- 0.5B – 405B
- Hardware
- from: Laptop
Biology and chemistry2022–2026
EvolutionaryScale / Chan Zuckerberg Biohub (ESM-2 — Meta AI) · USA
Protein language models: they understand amino acid sequences, predict structure (ESMFold2) and help with protein design. Since 2026 all open versions are under MIT.
- Protein embeddings for predicting properties (stability, solubility)
- Predicting 3D structures of proteins and complexes
- Screening enzyme and antibody design candidates before lab work
- Sizes
- 8M – 15B (ESM-2), 300M – 6B (ESM C), 1.4B (open ESM3)
- Hardware
- from: Laptop
Computer-use agentsGGUF2025–2026
H Company · France
A French model family for controlling a browser and computer: precisely finds the right element on screen and handles multi-step tasks. The latest Holo3 and 3.1 are open under Apache 2.0.
- Working in web portals and legacy software without an API
- Filling in forms and applications
- Testing interfaces against scenarios
- Sizes
- 0.8B – 235B-A22B
- Hardware
- from: Laptop
TranslationRU2025–2026
Tencent · China
Tencent translators for 33 languages; the first version won the WMT25 competition. Russian is supported. The small 1.8B version runs on a laptop; the new Hy-MT2 is under Apache 2.0.
- Translating documents while keeping formatting
- Translation with a set glossary of terms
- Translating correspondence with Chinese partners
- Sizes
- 1.8B – 30B-A3B
- Hardware
- from: Laptop
Search and RAGRUGGUF2023–2026
Jina AI · Germany
Strong multilingual embeddings with long context; v5-omni understands text, images and audio. Recent versions are open for non-commercial use only.
- Search across documents in many languages
- Search across images and scans
- Classification and clustering
- Sizes
- 33M – 3.8B
- Hardware
- from: Laptop
Image + textOllama2023–2026
LLaVA / LMMs-Lab (researchers from the USA and China) · USA / China
The open project that started the trend for image-plus-text models. The OneVision line understands photos, documents and video; training data and recipes are open.
- Answering questions about photos and screenshots
- Describing products from a photo
- Frame-by-frame video analysis
- Sizes
- 0.5B – 72B
- Hardware
- from: Laptop
MedicineOllama2023–2026
EPFL · Switzerland
Open medical models from Swiss EPFL, fine-tuned on clinical guidelines on top of various base models. Does not replace a doctor; decisions are made by a specialist.
- Answering staff questions based on clinical guidelines
- Draft discharge summaries for a doctor to review
- Searching medical literature
- Sizes
- 2B – 70B
- Hardware
- from: Laptop
Documents and OCRGGUF2025–2026
Shanghai AI Laboratory (OpenDataLab) · China
A popular open tool for converting PDFs to Markdown with its own small model. MinerU2.5-Pro was improved through data alone, without growing in size. Languages on the card: Chinese and English.
- Converting PDF reports and contracts to Markdown
- Recognising tables and formulas
- Preparing documents for RAG and search
- Sizes
- 0.9B – 1.2B
- Hardware
- from: Laptop
Text to speechRU2025–2026
OpenMOSS (Fudan University) · China
A speech synthesis family: multi-voice dialogue voicing (TTSD), fast synthesis for live conversation and the tiny Nano. Version 1.5 supports 30+ languages, including Russian.
- Voicing podcasts and dialogues
- Voice for an assistant
- Voice cloning
- Sizes
- 100M – 8.5B
- Hardware
- from: Laptop
Documents and OCRRUGGUF2025–2026
Baidu (PaddlePaddle) · China
A compact document parsing model from the popular PaddleOCR toolkit. Per the model card it supports 109 languages, including Russian; version 1.6 leads the OmniDocBench benchmark.
- Recognising invoices, contracts and delivery notes, including in Russian
- Recognising tables, formulas and stamps
- Converting scans to Markdown and JSON
- Sizes
- 0.9B
- Hardware
- from: Laptop
Text to speechRU2025–2026
Supertone · South Korea
Very fast, lightweight speech synthesis that runs directly on the device, without a GPU or the cloud. Supertonic 3 speaks 31 languages, including Russian.
- Voicing voice bot replies on an ordinary server
- Voiceover in offline and mobile apps
- Reading texts and notifications aloud
- Sizes
- about 99M
- Hardware
- from: Laptop
Forecasting2024–2026
THUML, Tsinghua University · China
A compact forecasting foundation model from the Tsinghua lab: trained on a large set of diverse series and fine-tunable on your own data.
- Forecasting demand and load
- Forecasting sensor readings on the shop floor
- Fine-tuning forecasts on your own history
- Sizes
- 84M (timer-base)
- Hardware
- from: Laptop
3D2024–2026
VAST (TripoSR together with Stability AI) · China
VAST family: a 3D model from a single photo. TripoSR runs in under a second, TripoSG gives cleaner geometry, TripoSplat builds a scene from Gaussian points.
- 3D product model from a photo
- Object assets for games and AR
- Quick 3D prototype for printing
- Sizes
- up to 1.5B
- Hardware
- from: Laptop
Plates and vehicles2025–2026
MorseTechLab · not disclosed
The most downloaded plate detector on Hugging Face: it finds the plate in a frame, and a separate model then reads it. Filming vehicles and people and storing the records is personal data processing: agree the procedure with a lawyer.
- Finding the plate in camera video
- Preparing crops for plate reading
- Testing a plate recognition idea without training
- Sizes
- a fine-tuned YOLO11, with an ONNX build available
- Hardware
- from: Laptop
Drawings and CADGGUF2026
Autodesk Research · USA
A model from Autodesk Research: from eight rendered views of a part it writes an executable CadQuery program. It was trained on synthetic data only. It produces a draft; an engineer checks and signs off the document.
- Getting a parametric model from a set of views of a part
- Converting finished geometry into editable code
- A draft model for a design office
- Sizes
- 2B (based on Qwen3-VL-2B)
- Hardware
- from: Laptop
TextRUGGUF2025–2026
Arcee AI · USA
An American family of MoE models trained from scratch: Nano, Mini and Large. Trinity-Large-Thinking (398B) reasons before answering.
- Agents with tool calling
- Reasoning tasks
- Corporate assistant on your own servers
- Sizes
- 6B – 398B-A13B
- Hardware
- from: Laptop
TextGGUF2025–2026
Baidu · China
Baidu's first open line: from a tiny 0.3B to MoE with 424 billion parameters, including versions that understand images. The mid-size 21B-A3B fits on one GPU; ERNIE-Image 8B draws images with text.
- Corporate assistant
- Analysis of documents and images
- Customer request classification
- Sizes
- 0.3B – 424B-A47B
- Hardware
- from: Laptop
Search and RAGRUOllama2024–2026
IBM · USA
Lightweight IBM embeddings for enterprise search, trained on data with clear rights. R2, released in 2026, became multilingual.
- Search across corporate documents
- RAG on a regular server without a GPU
- Reranking results
- Sizes
- 30M – 311M
- Hardware
- from: Laptop
Moderation and safetyOllama2024–2026
IBM · USA
IBM judge models: they catch harm, profanity and jailbreak attempts, and in RAG and agents check whether an answer is grounded in the documents. You can state your own rule in words.
- Checking bot requests and replies
- Finding made-up facts in knowledge-base answers
- Checking your own rules written as text
- Sizes
- 38M – 8B
- Hardware
- from: Laptop
Image + textOllama2025–2026
IBM · USA
Compact IBM models for business documents: tables, charts, forms, field-value pairs. The model card openly warns that it works best with English.
- Extracting fields from forms and invoices
- Turning charts and tables into data
- Answering questions about documents
- Sizes
- 2B – 4B
- Hardware
- from: Laptop
Text to speech2025–2026
Kyutai · France
Streaming speech recognition and synthesis models from the makers of Moshi: they start speaking and transcribing without waiting for the end of a phrase. Pocket TTS (100M) runs on a CPU. English, French and a few other European languages, no Russian.
- Streaming speech transcription for voice bots
- Voicing replies with minimal delay
- Speech synthesis on a server without a GPU (Pocket TTS)
- Sizes
- 100M (Pocket TTS) – 2.6B
- Hardware
- from: Laptop
TextRU2024–2026
Ivan Bondarenko (bond005), Novosibirsk State University · Russia
Russian-language models for working with documents rather than chatting: knowledge-base answers, extraction of entities and facts from Russian text, long context.
- Answers to questions based on internal documents
- Extracting names, dates and amounts from contracts
- Short summaries of long Russian texts
- Sizes
- 1.5B – 7.6B
- Hardware
- from: Laptop
Text analysisOllama2024–2026
NuMind · France
Models for template-based data extraction: give it a document or scan and a JSON field template, get a filled-in JSON back. NuExtract3 (4B) also converts scans to Markdown.
- Extracting company details, amounts and dates from invoices and contracts into JSON
- Parsing receipts, waybills and forms against a set template
- Converting scans to Markdown for search
- Sizes
- 0.5B – 8B
- Hardware
- from: Laptop
Search and RAGGGUF2025–2026
Octen · USA / Singapore
Qwen3-Embedding models fine-tuned by the startup Octen for search in legal, financial and medical texts. As of January 2026 the 8B version topped the RTEB leaderboard.
- Search across contracts and case law
- Search across financial reports
- Search across long documents up to 32K tokens
- Sizes
- 0.6B – 8B
- Hardware
- from: Laptop
Moderation and safety2026
OpenAI · USA
Finds and hides personal data: names, addresses, phone numbers, emails, account numbers, passwords. Runs even in the browser. Trained mostly on English.
- Removing personal data from text before sending it to cloud AI
- Finding passwords and keys in texts
- Anonymizing correspondence for analytics
- Sizes
- 1.5B (50M active)
- Hardware
- from: Laptop
TranslationRU2020–2026
Helsinki-NLP, University of Helsinki · Finland
More than a thousand small translators, each for its own language pair. Russian-English and back are available. Fast even on a regular CPU.
- Bulk translation of short texts
- Translation right on the server without a GPU
- Translating reviews and requests before analysis
- Sizes
- 25M – 240M
- Hardware
- from: Laptop
Fact-checking and judgesRU2025–2026
SberDevices (ai-forever) · Russia
Judge models that evaluate other AI models' answers in Russian: they score against a given criterion and explain the score in text.
- Automatic quality checks of Russian chatbot answers
- Comparing several models before choosing one
- Checking answers after fine-tuning
- Sizes
- 4B – 32B
- Hardware
- from: Laptop
Computer-use agents2024–2026
Show Lab (National University of Singapore) · Singapore
A lightweight model for working with interfaces: finds buttons and fields by description and performs actions on the web and on a phone. ShowUI-π can drag with the mouse.
- Clicking and filling in forms from a task description
- Web UI autotests
- An assistant on a low-end computer without the cloud
- Sizes
- 2B (ShowUI), about 500M (ShowUI-π)
- Hardware
- from: Laptop
ForecastingGGUF2025–2026
Datadog · USA
A Datadog forecasting model trained on server and application metrics. Especially strong for IT monitoring: load, latency, errors.
- Server load forecasting
- Anomaly detection in metrics
- Capacity planning
- Sizes
- 4M – 2.5B
- Hardware
- from: Laptop
Acoustic monitoring2023–2026
Xiaomi · China
Compact sound-labelling models from 5.5M to 86M, with ONNX and INT8 builds that run on an ordinary CPU and on a board next to the equipment. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.
- Labelling sound on modest hardware and on site
- Detecting alarm sounds and abnormal noise
- Fine-tuning for your own set of equipment sounds
- Sizes
- 5.5M - 86M
- Hardware
- from: Laptop
Acoustic monitoring2024–2026
Xiaomi · China
A general-purpose audio encoder trained on 272 thousand hours of speech, music and noise: it gives features on top of which you train your own classifier of abnormal sounds. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.
- Audio features for your own anomaly model
- Finding similar fragments in a recording archive
- Fine-tuning for the sounds of one production line
- Sizes
- 86M - 1.2B
- Hardware
- from: Laptop
Plates and vehicles2024–2026
ankandrew (open project) · not disclosed
A ready pipeline for plate recognition: plate detector and character reading in one package, with your own models pluggable. Filming vehicles and people and storing the records is personal data processing: agree the procedure with a lawyer.
- Getting plate recognition running quickly on site
- Automatic vehicle access by list
- Logging vehicle entry and exit
- Sizes
- a lightweight plate detector paired with XS and S reading models
- Hardware
- from: Laptop
Plates and vehicles2024–2026
ankandrew (open project) · not disclosed
Lightweight models that read characters from an already cropped license plate and run on an ordinary CPU. Filming vehicles and people and storing such records is personal data processing: agree the procedure and retention with a lawyer.
- Reading a plate at entry and exit
- Matching a plate against a whitelist of passes
- Going through archived camera footage
- Sizes
- XS and S models on the CCT architecture
- Hardware
- from: Laptop
Voice: speakers and soundRU2026
FireRedTeam (Xiaohongshu) · China
A speech and sound event detector: tells apart speech, singing and music. In a 102-language test (the FLEURS set, which includes Russian) it beat Silero VAD and TEN VAD. Has a streaming mode.
- Cutting recordings before speech recognition
- Separating speech from music and singing in broadcasts and videos
- Speech detection in voice bots
- Sizes
- compact, exact size not stated
- Hardware
- from: Laptop
Search and RAGRU2026
Microsoft · USA
Microsoft's 2026 multilingual embeddings with context up to 32K tokens; Russian is on the language list. The 270M and 0.6B versions run on a regular server, 27B is the most accurate.
- Multilingual knowledge base search
- Picking passages for RAG
- Search across long documents
- Sizes
- 270M – 27B
- Hardware
- from: Laptop
MedicineGGUF2025–2026
Zhejiang University · China
A medical model for text, images, 3D scans and video: from a light 4B to a large MoE. Does not replace a doctor; decisions are made by a specialist.
- Hints for doctors when reviewing images and CT scans
- Draft reports and discharge summaries
- Searching medical literature
- Sizes
- 4B – 235B-A22B
- Hardware
- from: Laptop
Image + textRUGGUF2023–2026
Shanghai AI Laboratory (OpenGVLab) · China
A large family of Chinese vision models sized from 1B to 241B. InternVL-U (4B) combines image understanding, generation and editing.
- Understanding documents, diagrams and charts
- Answering questions about photos
- Video analysis
- Sizes
- 1B – 241B-A28B
- Hardware
- from: Laptop
Plates and vehicles2022–2026
PaddlePaddle (Baidu) · China
A ready set of models for vehicle tasks: plate recognition, car color and type, counting entries and exits, spotting parking where it is not allowed. Filming vehicles and people is personal data processing: agree the procedure with a lawyer.
- Counting traffic flow
- Identifying car type and color
- Reading the plate at the entrance
- Sizes
- a set of models: vehicle detector, attributes, plate reading on PP-OCR
- Hardware
- from: Laptop
Computer vision2023–2026
Meta · USA
Selects any object in photos and videos with a click or a box. The basis for background removal and object counting.
- Background removal from product photos
- Counting objects in photos
- Data labeling for training
- Sizes
- 91M – ~0,85B
- Hardware
- from: Laptop
Text analysisRU2026
Tatar NLP Community · not disclosed
A recent set of models for Tatar: morphological analysis on several base models, question answering about Tatar and Russian place names, and Mistral and GPT-2 fine-tunes for Tatar.
- Morphological analysis of Tatar texts
- Answering questions about place names
- Generating text in Tatar
- Sizes
- 178M for the morphology models, 7B for the Mistral fine-tune
- Hardware
- from: Laptop
Plates and vehicles2026
Autolane · not disclosed
A recent set of plate recognition weights: two plate detectors and a reading model, trained on US plates, so the Russian format needs fine-tuning. Filming vehicles and people is personal data processing: agree the procedure with a lawyer.
- Finding the plate in a frame
- Reading the plate characters
- Running on cameras and single-board computers
- Sizes
- RF-DETR and YOLOX-S detectors, CCT-S for character reading
- Hardware
- from: Laptop
Computer-use agents2025–2026
Alibaba (Tongyi Lab, X-PLUG) · China
Models for controlling phones and computers from the Mobile-Agent project: they work with Android, Windows, macOS and the browser; version 1.5 has a reasoning mode.
- Automating actions in mobile apps
- Working in desktop software without an API
- Testing apps against scenarios
- Sizes
- 2B – 32B
- Hardware
- from: Laptop
Math and reasoningGGUF2026
LM Provers (CMU, Hugging Face, ETH Zurich, Project Numina) · USA, Switzerland, France
A small 4B model on Qwen3 that writes mathematical proofs in plain language almost at the level of large models. Runs on a laptop.
- Checking the logic of reasoning and workings
- Step-by-step explanations of solutions
- Training and olympiad preparation
- Sizes
- 4B
- Hardware
- from: Laptop
CodeOllama2024–2026
Alibaba (Qwen team) · China
The broadest open coding family: from 0.5B for autocompletion to 480B for agents. Qwen3-Coder-Next (80B, 3B active) works as a developer agent on a single GPU.
- Code autocompletion in the editor
- An agent that edits code in the repository on its own
- Writing and refining scripts, SQL and integrations
- Sizes
- 0.5B – 480B-A35B
- Hardware
- from: Laptop
Tabular data2025–2026
Inria (Soda team) · France
An open tabular model from the creators of scikit-learn: classifies and predicts from examples without training and handles tables of up to hundreds of thousands of rows. The license allows business use.
- Predicting customer churn
- Scoring applications and deals
- Classifying customers from 1C and CRM data
- Sizes
- about 25–30M
- Hardware
- from: Laptop
Medicine2023–2026
Stanford AIMI · USA
Stanford models for chest X-rays: they describe the image and prepare a draft report. Does not replace a doctor; decisions are made by a specialist.
- A draft X-ray description for the radiologist
- Hints for doctors when reviewing images
- Checking reports for completeness
- Sizes
- 3B – 8B
- Hardware
- from: Laptop
TextRUGGUF2024–2026
UTTER consortium (Unbabel, universities of Lisbon, Edinburgh, Amsterdam and others) · European Union
European language models trained on all EU languages and several others, with a focus on translation. Russian is supported. Permissive license.
- Translation and localization of texts
- Answering questions in different languages
- Draft emails for foreign partners
- Sizes
- 1.7B – 22B
- Hardware
- from: Laptop
TextRUOllama2023–2026
Technology Innovation Institute (TII) · UAE
A family from Abu Dhabi: from the early Falcon 40B and 180B to hybrid Falcon-H1 and tiny Falcon-H1-Tiny models of 90–600M parameters for devices.
- Assistant and answers based on documents
- Running on low-end hardware and devices
- Tool calling in simple agents
- Sizes
- 90M – 180B
- Hardware
- from: Laptop
Documents and OCRRUOllama2026
Zhipu AI (Z.ai) · China
A lightweight OCR model from Zhipu for document parsing. The model card lists Russian among supported languages; built for high load and low-end hardware.
- Recognising invoices, contracts and delivery notes, including in Russian
- Recognising tables and formulas
- Extracting fields to JSON
- Sizes
- 0.9B
- Hardware
- from: Laptop
TextGGUF2024–2026
AI21 Labs · Israel
A hybrid of Transformer and Mamba with a window of up to 256K tokens: handles long documents faster than conventional models. Jamba2 focuses on accurate, source-based answers.
- Answers based on long policies and contracts
- Knowledge-base search (RAG)
- Summaries of large documents
- Sizes
- 3B – 398B-A94B
- Hardware
- from: Laptop
MedicineOllama2025–2026
Google · USA
Google's medical version of Gemma: reads medical texts and images (X-ray, dermatology, histology). A tool for doctors and developers; does not replace a doctor, decisions are made by a specialist.
- Draft discharge summaries and reports for a doctor to review
- Hints for doctors when reviewing images
- Searching and summarising medical literature
- Sizes
- 4B – 27B
- Hardware
- from: Laptop
TextOllama2024–2026
Allen Institute for AI (Ai2) · USA
Fully open models: not only the weights but also the data, training code and intermediate checkpoints are published. Useful when transparent provenance matters.
- Assistant and answers based on documents
- Reasoning tasks (Think versions)
- Fine-tuning on your data with a clear model history
- Sizes
- 1B – 32B
- Hardware
- from: Laptop
TextRUOllama2023–2026
Microsoft · USA
Small Microsoft models trained on carefully selected data: strong at logic and math for their modest size. Versions with images and speech are available.
- Assistant on a laptop or your own server
- Reasoning and calculation tasks
- Analysis of images and diagrams (vision versions)
- Sizes
- 1.3B – 42B-A6.6B
- Hardware
- from: Laptop
Search and RAGRUOllama2025–2026
Alibaba (Qwen) · China
Embeddings and rerankers based on Qwen3, among the best open ones for multilingual search, including Russian. VL versions search images, screenshots and video.
- Knowledge base search for RAG
- Reranking results before answering
- Search across scans, slides and screenshots
- Sizes
- 0.6B – 8B
- Hardware
- from: Laptop
Voice: speakers and soundRU2025–2026
Daily (Pipecat) · USA
Uses intonation to tell whether a person has finished a thought or just paused, so a voice bot does not interrupt. Version 3 is 8 MB, runs on a CPU and understands 23 languages, including Russian.
- Voice bot does not interrupt the customer during pauses
- Fast reply when the customer has really finished
- An add-on to a standard speech detector in voice assistants
- Sizes
- 8M (v3) – 580M (v1)
- Hardware
- from: Laptop
TranslationRUOllama2026
Google · USA
Translators based on Gemma 3 for 55 languages that can also translate text in images. Russian is supported. The 4B version fits on a laptop.
- Translating documents and correspondence
- Translating text from screenshots and photos
- Localizing websites and apps
- Sizes
- 4B – 27B
- Hardware
- from: Laptop
Search and RAG2026
Voyage AI (MongoDB) · USA
The only open model in the Voyage 4 line: its vectors are compatible with the paid larger versions, so you can start locally and move to the API later.
- Document search on your own server
- RAG for small knowledge bases
- Finding similar texts
- Sizes
- about 340M
- Hardware
- from: Laptop
Computer vision2023–2026
Ultralytics · USA
The most widely used real-time object detector: finds and marks items in video even on modest hardware. YOLOv5 came out back in 2020; the catalog starts from YOLOv8.
- Counting people, cars and goods on video
- Checking hard hats and workwear
- Spotting defects on the production line
- Sizes
- 2.4M – 68M
- Hardware
- from: Laptop
Computer visionGGUF2024–2025
ByteDance and the University of Hong Kong · China
Estimates depth, the distance to every point, from one ordinary photo or video. DA3 reconstructs scene geometry from several frames.
- Estimating distances and volumes from a camera
- Depth effects for photo and video
- Navigation for robots and drones
- Sizes
- 25M – 1.4B
- Hardware
- from: Laptop
Text2025
Naver · South Korea
Open smaller models from Korea's Naver: from 0.5B to 32B, including reasoning Think versions and multimodal versions that understand images.
- Lightweight Korean-English assistant
- Analysis of images and documents
- Text classification
- Sizes
- 0.5B – 32B
- Hardware
- from: Laptop
TextGGUF2023–2025
Inception (G42), MBZUAI and Cerebras · UAE
A model family for Arabic and English, including Gulf dialects. Suits companies working with Arabic-speaking customers and government bodies in the region.
- A chatbot in Arabic and English
- Translating and summarising documents in Arabic
- Classifying customer requests
- Sizes
- 256M – 70B
- Hardware
- from: Laptop
Computer-use agentsGGUF2025
Alibaba (Tongyi-MAI) · China
Compact Alibaba models for working in smartphone and computer interfaces: they find elements and complete multi-step tasks. The agent acts on the user's behalf inside their apps, so access rights and limits are set before launch. The follow-up line, Qwen-UI-Agent, was announced in July 2026, but its weights have not been released.
- Automating actions in mobile apps
- Working in software without an API
- UI autotests
- Sizes
- 2B – 8B
- Hardware
- from: Laptop
Speech to textRU2025
Meta · USA
Speech recognition for 1,600+ languages, including Russian and rare languages no system supported before. A new language can be added from a few examples.
- Transcription in rare and local languages
- Digitizing oral archives
- Subtitles in many languages
- Sizes
- 300M – 7B
- Hardware
- from: Laptop
Computer vision2025
Meta · USA
Meta's family of encoders for images and video, and with PE-AV also for audio. PE-Core searches by text more accurately than SigLIP 2 (per Meta); small versions are available.
- Search photos and videos by description
- Catalog labeling and tagging
- Search across audio and video (PE-AV)
- Sizes
- size not stated on the model card
- Hardware
- from: Laptop
Speech to text2024–2025
Alibaba (Tongyi, FunAudioLLM) · China
Alibaba's set of fast speech recognition models, primarily for Chinese and Asian languages. SenseVoice also detects emotions and sound events.
- Transcribing calls
- Detecting emotions in the voice
- Recognizing laughter, music and other sounds
- Sizes
- about 230M – 800M
- Hardware
- from: Laptop
TextRUGGUF2024–2025
Vikhr Models · Russia
Russian-language fine-tunes of open models (Mistral, Qwen, Llama) by the independent Vikhr team, with compact versions for a regular PC. Borealis is an audio model for recognizing and understanding Russian speech.
- Russian-language assistant on your own PC or server
- Knowledge-base answers (RAG)
- Texts and emails in Russian
- Sizes
- 0.5B – 24B
- Hardware
- from: Laptop
Speech to textRU2024–2025
Mihaj Dolgushin · not disclosed
About two dozen Whisper, wav2vec2 and WavLM fine-tunes for Karelian, including recordings where the speaker switches from Karelian to Russian. The model cards are empty, so quality must be checked on your own recordings.
- Transcribing field and archive recordings in Karelian
- Subtitles for Karelian-language material
- Handling recordings that mix Karelian and Russian
- Sizes
- from 300M to 1B across the different models
- Hardware
- from: Laptop
TextOllama2025
Deep Cogito · USA
Fine-tuned Llama, Qwen and DeepSeek models with a hybrid mode: answer immediately or reason first. The 671B v2.1 flagship spends noticeably fewer tokens on reasoning than DeepSeek R1.
- A chat assistant with a reasoning mode
- Writing code and calling tools
- Answering complex questions about documents
- Sizes
- 3B – 671B
- Hardware
- from: Laptop
TextOllama2023–2025
Nous Research · USA
Nous Research fine-tunes on top of Llama, Mistral, Qwen and Seed-OSS. Valued for precise instruction following, function calling and strict JSON output; they refuse less often than the originals; Hermes 4 has a reasoning mode.
- Agents that call functions and APIs
- Data extraction in strict JSON format
- Assistant with flexible role and tone settings
- Sizes
- 3B – 405B
- Hardware
- from: Laptop
Satellite and geo2025
IBM and the European Space Agency (ESA) · USA / Europe
A multimodal Earth model: understands optical and radar imagery, terrain, vegetation index and land use maps, and can generate a missing data type (for example, a "see-through-clouds" image from radar).
- Analyzing fields and forests even in cloudy weather using radar imagery
- Land use maps for assessing plots
- Flood and wildfire assessment (ready-made fine-tunes available)
- Sizes
- tiny – large (checkpoints from ~200 MB to ~3.8 GB)
- Hardware
- from: Laptop
Computer vision2023–2025
Meta · USA
Meta's open reproduction of CLIP with a transparent data collection recipe. MetaCLIP 2 is trained on multilingual data from around the world. Non-commercial license only.
- Image search by text
- Image classification without training
- Search research and prototypes
- Sizes
- 0.15B – 3.6B
- Hardware
- from: Laptop
Acoustic monitoring2025
Carnegie Mellon University and co-authors (the ESPnet project) · USA
A fully open reproduction of BEATs: code, training recipes and weights are all published. Teams pick it when they need a transparent base for their own sound model. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.
- A transparent base for your own audio model
- Fine-tuning on your own equipment recordings
- Labelling sound events
- Sizes
- base and large versions, exact sizes are listed on the model cards
- Hardware
- from: Laptop
Text to speechRU2022–2025
Silero · Russia
Lightweight Russian speech synthesis that runs on a regular CPU. Version v5 added CIS languages and languages of Russia's peoples: Tatar, Bashkir, Yakut, Kazakh and others.
- Voicing voice bot replies
- Reading texts in Russian
- Voices in the languages of Russia's peoples
- Sizes
- tens of megabytes
- Hardware
- from: Laptop
Voice: speakers and soundRU2020–2025
Silero · Russia
The most popular open speech detector: tells voice apart from silence and noise. Processes an audio chunk in under a millisecond on a single CPU core; trained on recordings in more than 6,000 languages.
- Cutting calls and recordings before speech recognition
- Detecting when the customer is speaking in a voice bot
- Filtering out silence and noise to save on transcription
- Sizes
- about 2 MB
- Hardware
- from: Laptop
Deepfake detection2025
National Institute of Informatics, Yamagishi Lab · Japan
Seven speech encoders (wav2vec 2.0, XLS-R, MMS, HuBERT) post-trained to tell live speech from synthetic. The authors note themselves that quality depends heavily on the dataset; a human reviews the output.
- Checking audio recordings for synthesis
- Fine-tuning for your own language and recording channel
- Comparing several encoders on your own data
- Sizes
- 0,3B – 2B
- Hardware
- from: Laptop
ForecastingGGUF2024–2025
Amazon · USA
Amazon forecasting models, among the most downloaded. Chronos-2 takes external factors into account: prices, promotions, weather.
- Demand forecasting with promotions and prices
- Inventory planning
- Forecasting revenue and customer flow
- Sizes
- 8M – 710M
- Hardware
- from: Laptop
Computer vision2023–2025
IDEA Research · China
Finds any objects in an image from a text description, without training on your data: "red box", "person without a hard hat". Rex-Omni is the new VLM-based generation.
- Finding objects by description without labeling
- Automatic data labeling for training
- Checking photos against requirements
- Sizes
- 172M – 3B
- Hardware
- from: Laptop
Recommenders2025
MiniOneRec open project · China
A small open generative recommender at 1.5B with published checkpoints and a full training pipeline. Handy as a learning and starter option; a real store needs fine-tuning on its own orders.
- A quick recommendation prototype on your own data
- Testing ideas before running a large model
- Training a team to work with generative recommendations
- Sizes
- 1.5B
- Hardware
- from: Laptop
Visual document search2025
Illuin Technology, EPFL, CentraleSupélec · France
A compact (250M) model for searching document pages as images. According to the authors, it matches models 10 times larger and runs without a GPU.
- Search across scans and PDFs on a modest server
- Indexing document archives
- Search across slides and manuals
- Sizes
- 250M
- Hardware
- from: Laptop
Search and RAGRUOllama2024–2025
Mixedbread · Germany
Embeddings and rerankers from Germany's Mixedbread. mxbai-embed-large is one of the most downloaded English search models; the v2 rerankers cover 100+ languages, including Russian.
- Search across a knowledge base
- Reranking results before a bot answers
- Product catalog search
- Sizes
- 17M – 1.5B
- Hardware
- from: Laptop
Documents and OCRRUGGUF2025
Nanonets · USA / India
A model that converts documents to Markdown with tables, stamps, signatures, checkboxes and watermarks. The OCR2 model card lists Russian among its languages.
- Recognising invoices, contracts and delivery notes, including in Russian
- Recognising stamps, signatures and marks
- Handwriting recognition
- Sizes
- 1.5B – 3B
- Hardware
- from: Laptop
Voice: speakers and sound2022–2025
NVIDIA · USA
NVIDIA models for "who is speaking": TitaNet recognizes a specific person's voice, Sortformer splits a recording into up to 4 speakers, including live during a call.
- Real-time speaker tagging in conversations
- Checking that the same person is calling (voiceprint)
- Preparing meeting transcripts
- Sizes
- 23M (TitaNet) – 117M (Sortformer)
- Hardware
- from: Laptop
Image + textRUOllama2023–2025
Alibaba (Qwen team) · China
One of the strongest open vision models: reads documents, tables, charts and video, and works with user interfaces. Since Qwen3.5, vision is built directly into the main Qwen model.
- Extracting data from scanned invoices and delivery notes
- Analysing photos of products and shelves
- Analysing video and camera footage
- Sizes
- 2B – 235B-A22B
- Hardware
- from: Laptop
Search and RAGOllama2023–2025
BAAI (Beijing Academy of Artificial Intelligence) · China
Some of the most popular embeddings for search and RAG. The main v1.5 versions target English and Chinese; for Russian, BAAI has a separate model, bge-m3.
- Search across English-language documents
- Picking passages for chatbot answers (RAG)
- Code search (bge-code)
- Sizes
- 24M – 9B
- Hardware
- from: Laptop
Satellite and geo2023–2025
IBM and NASA · USA
Foundation models for Landsat and Sentinel-2 satellite imagery that account for image time series. Ready-made fine-tunes for floods, burn scars and crop types, plus a separate weather model, WxC.
- Mapping crops and field condition over the season
- Assessing flood zones and burn scars after natural disasters
- Monitoring changes in buildings and land use
- Sizes
- tiny – 600M (imagery), 2.3B (Prithvi WxC weather)
- Hardware
- from: Laptop
Text to SQLGGUF2024–2025
Prem AI · UK
A text-to-SQL model of just 1B parameters, designed to run locally so the database never leaves for external services.
- Local translation of questions into SQL with no internet access
- Query hints on modest hardware
- Embedding into internal analytics tools
- Sizes
- 1B
- Hardware
- from: Laptop
Voice: speakers and sound2022–2025
pyannoteAI (Hervé Bredin) · France
The most widely used open tool for splitting a recording by speaker: who spoke and when. Usually paired with speech recognition. Weights are issued after a short form on HF.
- Tagging calls: which part is the agent, which is the customer
- Meeting minutes with speaker labels
- Preparing recordings for transcription and analysis
- Sizes
- a few million parameters
- Hardware
- from: Laptop
Moderation and safetyRUGGUF2025
Alibaba (Qwen) · China
Safety filters for 119 languages, Russian among them. The Stream version checks a bot's reply while it is being generated and can cut it off on the fly.
- Filtering bot requests in Russian
- Stopping a dangerous reply during generation
- Labeling messages by risk category
- Sizes
- 0.6B – 8B
- Hardware
- from: Laptop
Deepfake detection2023–2025
IBM Research and The Chinese University of Hong Kong · USA
An AI-text detector trained together with a paraphraser: it was deliberately taught not to give up when the text has been rewritten. It errs in both directions; a human reviews the output.
- Checking texts that may have been rewritten after generation
- First-pass filtering in a newsroom or admissions office
- Comparison against simpler detectors
- Sizes
- about 355M (RoBERTa-large)
- Hardware
- from: Laptop
Documents and OCR2025
IBM and Hugging Face · USA
Tiny models for the open Docling document converter: they turn a page into markup with tables, formulas and code. Run on an ordinary laptop.
- Converting PDFs and scans to Markdown for search and RAG
- Recognising tables in reports
- Processing invoices and contracts on an ordinary PC
- Sizes
- 256M – 258M
- Hardware
- from: Laptop
Drawings and CAD2025
Manycore Research · China
From a point cloud of a room or a walkthrough video it builds a structured plan: walls, doors, windows and objects with coordinates and sizes. It is a draft survey; final areas are confirmed by a specialist.
- Building a floor plan from a 3D scan of a space
- Extracting walls, doors and windows with dimensions
- Draft measurements before a renovation or a move
- Sizes
- 0.5B - 1B
- Hardware
- from: Laptop
Speech to textRU2023–2025
Alpha Cephei · Russia
Offline Russian speech recognition that runs even on a Raspberry Pi or a phone, without internet. Streaming models for live audio and simple Russian speech synthesis, Vosk TTS, are available.
- Transcribing Russian calls and recordings without the cloud
- Voice control in apps and kiosks
- Low-latency streaming speech recognition
- Sizes
- about 45 MB – 1.8 GB
- Hardware
- from: Laptop
Voice: speakers and sound2024–2025
Alibaba (Tongyi Lab) · China
Alibaba's set of speech cleanup models: noise suppression, separating overlapping voices, upscaling audio to 48 kHz, and isolating a voice using video of the speaker's face.
- Noise suppression in conversation recordings
- Separating two voices speaking at once
- Improving old and phone recordings
- Sizes
- under 1B
- Hardware
- from: Laptop
Deepfake detection2023–2025
The Chinese University of Hong Kong, Shenzhen (SCLBD) · China
Dozens of open face-swap detectors for video and photo under one codebase with ready weights. A detector errs in both directions: its output is a reason for a human to check, not proof of a forgery.
- First-pass check of a submitted video or selfie
- Comparing several detectors on your own data
- Fine-tuning a detector for your own flow of applications
- Sizes
- Xception- and EfficientNet-class detectors, tens of millions of parameters
- Hardware
- from: Laptop
Computer vision2023–2025
Meta · USA
Foundation models that turn an image into a numeric "fingerprint". They are used to build similar-image search, classification and segmentation without large labeled datasets.
- Finding similar products and photos
- Image classification on small datasets
- Base for your own quality-control models
- Sizes
- 21M – 7B
- Hardware
- from: Laptop
Math and reasoningGGUF2025
Moonshot AI and Project Numina · China, France
Models for formal proofs in Lean 4 from Moonshot AI (Kimi) and Numina. Small versions from 0.6B run on a laptop.
- Formal verification of mathematical workings
- Translating a problem from plain language into Lean
- Training and olympiad preparation
- Sizes
- 0.6B – 72B
- Hardware
- from: Laptop
Search and RAGRU2023–2025
lingtrain · not disclosed
A set of LaBSE fine-tunes that turn sentences into vectors: Buryat, Mari, Udmurt, Ingush, Chuvash, Sakha and Kalmyk. Trained on pairs with Russian; quality differs by language.
- Aligning parallel texts in Russian and a national language
- Semantic search across bilingual archives
- Building training sets for translation
- Sizes
- LaBSE fine-tunes; parameter count is not stated on the cards
- Hardware
- from: Laptop
Faces2025
ByteDance · China
Transformer-based face recognition from ByteDance, one of the most accurate open models on benchmarks. Weights are published in ONNX format but are non-commercial.
- Comparing faces and searching a photo database
- Research on recognition accuracy
- Access control prototypes
- Sizes
- ViT-T – ViT-L
- Hardware
- from: Laptop
Text analysisRUGGUF2025
Johns Hopkins University (JHU CLSP) · USA
A multilingual encoder trained on more than 1800 languages. The list includes Tatar, Bashkir, Chuvash, Udmurt, Buryat, Komi, Ingush and other languages of Russia. A base for classifiers and search over such texts.
- Classifying requests and documents in national languages
- Semantic search over texts in rare languages
- Extracting names, dates and titles from text
- Sizes
- 140M and 307M
- Hardware
- from: Laptop
ForecastingGGUF2024–2025
Salesforce · USA
Salesforce's universal forecasting model for series with different frequencies and many variables. Weights are open for research only.
- Research forecasting pilots
- Comparison with other forecasting models
- Forecasts across many related series
- Sizes
- 11M – 311M
- Hardware
- from: Laptop
Acoustic monitoring2025
Google DeepMind · USA
A model for acoustic monitoring of nature: it recognises about 15,000 species and provides features for your own tasks, and the license allows commercial use. A microphone on site also records people voices, which is personal data, so check the procedure with a lawyer.
- Monitoring the sound background of a site or water area
- Environmental audio features for your own model
- Selecting events from round-the-clock recordings
- Sizes
- size not stated on the model card
- Hardware
- from: Laptop
TextRU2024–2025
Lomonosov Moscow State University Research Computing Center, LAIR lab (RefalMachine) · Russia
Qwen models adapted for Russian: a new tokenizer plus further training on Russian texts. As a result, Russian text is generated up to twice as fast as with the original model of the same size.
- Russian-language assistant on your own server
- Answers based on company documents (RAG) in Russian
- Analysis and summaries of long Russian texts
- Sizes
- 1.5B – 32B
- Hardware
- from: Laptop
Text analysis2023–2025
University of Texas at Arlington · USA
A classifier from an IEEE S&P study: it separates ordinary requests to a language model from requests that order text and a page meant to deceive people. A human makes the decision on a disputed operation; automatic blocking without review is not acceptable.
- Flagging assistant prompts that look like preparation for deception
- Checking campaign texts before they are sent
- Filling internal filtering rules with examples
- Sizes
- about 125M (based on RoBERTa-base)
- Hardware
- from: Laptop
Voice: speakers and soundRU2023–2025
Community (xbgoose and others), Dusha dataset from SberDevices · Russia
Models that detect emotion from voice in Russian speech: neutral, anger, positive, sadness. Trained on the open Dusha dataset from SberDevices.
- Finding calls with irritated customers
- Assessing the tone of operator conversations
- Prioritizing complaints in a call center
- Sizes
- 21M – 316M
- Hardware
- from: Laptop
Photo editingGGUF2024–2025
Nankai University · China
An open MIT-licensed model for precise object segmentation and background removal. RMBG-2.0 is built on it. Versions for 2K and for hair and semi-transparent edges.
- Bulk background removal from product photos
- Precise masks for design and print
- Cutting out people with hair for advertising
- Sizes
- about 220M (lightweight lite versions available)
- Hardware
- from: Laptop
Visual document search2024–2025
Illuin Technology (ViDoRe team) · France
Searches PDFs and scans as images: pages do not need to be OCR'd first, the model finds the right one for a question directly, including tables and charts. Trained on English.
- Search across scans, presentations and PDFs
- RAG over documents with tables and charts
- Search across technical documentation
- Sizes
- 256M – 3B
- Hardware
- from: Laptop
Fact-checking and judges2024–2025
OpenCompass (Shanghai AI Laboratory) · China
A line of judges from the team behind open model benchmarks: they score answers and check them against a reference. The judge itself makes mistakes and does not replace manual review on important tasks.
- Scoring model answers against set criteria
- Checking an answer against a reference solution
- Comparing several models on your own data
- Sizes
- 1.5B – 32B
- Hardware
- from: Laptop
Math and reasoningOllama2025
Agentica (Berkeley, Sky Computing Lab) and Together AI · USA
Small models fine-tuned with reinforcement learning: DeepScaleR (1.5B) solves olympiad maths, DeepCoder writes code, DeepSWE works as a developer agent. Recipes and data are open.
- Solving maths problems with step-by-step working
- Generating and checking code
- An agent for fixing bugs in a repository
- Sizes
- 1.5B – 32B
- Hardware
- from: Laptop
Finance2025
Tsinghua University (NeoQuasar) · China
A foundation model for market candlestick data: trained on data from more than 45 exchanges, it forecasts prices and volumes. The largest version, large, is not open.
- Forecasting candlesticks and trading volumes
- Volatility estimation
- A base for fine-tuning on your own series
- Sizes
- 4.1M – 102M
- Hardware
- from: Laptop
Medicine2025
Google · USA
Google's lightweight encoder for medical images and text, the same one inside MedGemma. Sorts images and finds similar ones. Does not replace a doctor; decisions are made by a specialist.
- Finding similar images in a clinic's archive
- Pre-sorting images for a doctor
- A base for your own image classifiers
- Sizes
- about 0.9B
- Hardware
- from: Laptop
TextRUOllama2024–2025
Hugging Face · USA
Tiny open Hugging Face models for phones and laptops. SmolLM3 (3B) can reason and handle long context; the full training recipe is open.
- Simple on-device assistant
- Classification and routing of requests
- Base for fine-tuning on a narrow task
- Sizes
- 135M – 3B
- Hardware
- from: Laptop
Speech to textRU2025
T-Bank · Russia
A compact T-Bank streaming model for recognizing Russian speech in phone calls. Works in real time even without a GPU.
- Transcribing phone calls
- Voice robots on the line
- Call quality control
- Sizes
- 72M
- Hardware
- from: Laptop
Voice: speakers and sound2025
Agora (TEN project) · USA / China
A lightweight speech detector for real-time voice assistants: it notices the start and end of a phrase faster than Silero VAD. Runs on servers, phones and in the browser.
- Zero-lag speech detection in a voice bot
- Fast assistant response at the end of a phrase
- Use in mobile apps and the browser
- Sizes
- very small, the library is smaller than Silero VAD
- Hardware
- from: Laptop
Math and reasoning2025
NVIDIA · USA
NVIDIA models for maths and reasoning based on Qwen. AceReason was fine-tuned with reinforcement learning first on maths, then on code.
- Calculations and formula checks
- Complex analytics with step-by-step breakdowns
- Working through programming problems
- Sizes
- 1.5B – 72B
- Hardware
- from: Laptop
Drawings and CAD2025
AIRI, Lomonosov Moscow State University and Innopolis University · Russia
A successor to CAD-Recode: it builds a CAD model as CadQuery code from three kinds of input at once - a point cloud, an image and a text description. It produces a draft; an engineer checks and signs off the document.
- Building a CAD model from a photo of a part
- Recovering a model from a 3D scan
- A draft part from a short text description
- Sizes
- 2.2B (based on Qwen2-VL)
- Hardware
- from: Laptop
Text to speechRU2025
Misha Yakovlev (Misha24-10) · not disclosed
Chuvash speech synthesis: an F5-TTS fine-tune on top of the Russian version, trained on 24 hours of Common Voice recordings. It can copy a voice from a sample — only with the voice owner’s consent. The author calls it an experiment, so check quality on your own texts.
- Reading Chuvash texts aloud
- Voice prompts and announcements
- Audio versions of learning material
- Sizes
- parameter count is not stated on the model card
- Hardware
- from: Laptop
Voice: speakers and sound2024–2025
RVC-Boss and community · China
Speech synthesis with voice cloning: a 5-second sample is enough, and after fine-tuning on a minute of recording the voice sounds noticeably more accurate. Use only with the voice owner's consent.
- Voicing texts with a specific narrator's voice
- Voice for a bot or assistant
- Dubbing training videos
- Sizes
- under 1B
- Hardware
- from: Laptop
Plates and vehicles2023–2025
Hezar AI · Iran
Character reading for Iranian license plates; the model is small and runs without a GPU. It was trained on another country plates, so the Russian format needs fine-tuning. Filming vehicles and people is personal data processing: agree the procedure with a lawyer.
- Reading a plate from a cropped image
- Using the architecture as an example for your own plate format
- Fine-tuning reading on your own footage
- Sizes
- a compact CRNN model
- Hardware
- from: Laptop
Search and RAGGGUF2024–2025
TechWolf · Belgium
A model from a Belgian HR company: it turns job titles into vectors so you can find similar vacancies and resumes. A human makes the decision about a candidate; automatic screening without review must not be used.
- Matching job titles coming from different sources
- Finding similar vacancies and resumes by meaning
- Cleaning up the company job title reference list
- Sizes
- 109M – 278M
- Hardware
- from: Laptop
CybersecurityGGUF2023–2025
Clouditera · China
A Chinese open family for cybersecurity: reviewing vulnerabilities, analysing logs and traffic, explaining commands and scripts.
- Reviewing vulnerabilities and drafting fix recommendations
- Analysing logs and reconstructing an attack chain
- Explaining suspicious commands and scripts
- Sizes
- 1.5B – 14B
- Hardware
- from: Laptop
Fact-checking and judges2024–2025
Skywork (Kunlun Tech) · China
Reward models: they score how good a language model's answer is for the user. Used for fine-tuning your own models and picking the best of several answers.
- Choosing the best of several bot answers
- Scoring answer quality during model fine-tuning
- Comparing models before rollout
- Sizes
- 0.6B – 27B
- Hardware
- from: Laptop
Robotics2025
Hugging Face · USA
A small robot control model that runs on a regular laptop. Trained on open data from the LeRobot community, suited to low-cost robot arms.
- Controlling a low-cost robot arm
- Quick robotization pilots and demos
- Training staff and students
- Sizes
- 450M
- Hardware
- from: Laptop
TranslationRUGGUF2024–2025
Unbabel · Portugal
Language models tailored for translation and multilingual text work: translating, editing, and assessing translation quality. Russian is supported. Non-commercial license.
- Translation that respects context and terminology
- Post-editing machine translation
- Assessing the quality of a finished translation
- Sizes
- 2B – 72B
- Hardware
- from: Laptop
Rerankers2023–2025
Stanford NLP, later Answer.AI and LightOn · USA and France
A different search principle: every word of the question is compared with every word of the document, not the two texts as a whole. The index is heavier than with ordinary embeddings. The model cards list English.
- Search across a knowledge base of long documents
- Reordering retrieved passages
- Search across policies and technical documentation
- Sizes
- about 33M – 150M
- Hardware
- from: Laptop
TextOllama2025
DeepSeek · China
A reasoning model that thinks step by step before answering. Strong at calculations, logic and code; compact distilled versions are available.
- Complex calculations and logic checks
- Analysis of contracts and internal policies
- Help for developers
- Sizes
- 1,5B – 671B
- Hardware
- from: Laptop
Acoustic monitoring2024–2025
Shanghai Jiao Tong University and Peng Cheng Laboratory · China
A self-supervised sound understanding model that is markedly cheaper to train on your own data than its predecessors. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.
- Training your own audio model on modest hardware
- Audio features for spotting abnormal operating modes
- Labelling sound events on a site
- Sizes
- 90M (base) and 309M (large)
- Hardware
- from: Laptop
CodeRU2025
MTS AI (MWS AI) · Russia
A small coding assistant from MTS AI that understands requests in Russian. Runs locally, with plugins for VS Code and JetBrains.
- Code suggestions and completion in the editor
- Code explanations in Russian
- Drafts of tests and documentation
- Sizes
- 1.5B
- Hardware
- from: Laptop
Text analysisRU2023–2025
deepvk (VK) · Russia
Russian encoders from the VK team: RuModernBERT reads long texts, USER produces vectors for search, GeRaCl classifies texts by topic without training.
- Classifying requests without labeled data
- Knowledge base search in Russian
- Analyzing long contracts
- Sizes
- 35M – 360M
- Hardware
- from: Laptop
Forecasting2025
THUML, Tsinghua University · China
A forecasting model that returns a set of possible scenarios rather than a single line — useful when you need a range for demand or load, not one number.
- Forecasting demand with a range of values
- Planning stock while accounting for spread
- Forecasting load on services and staff
- Sizes
- 128M (sundial-base)
- Hardware
- from: Laptop
Acoustic monitoring2024–2025
MIT CSAIL and MIT-IBM Watson AI Lab · USA
A sound understanding model built on state spaces instead of a transformer: it handles recordings hours long, which suits continuous listening to a production line. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.
- Processing long continuous recordings
- Finding a rare event across a multi-hour shift
- Labelling sound events on a site
- Sizes
- 30M (small) and 49M (medium)
- Hardware
- from: Laptop
Acoustic monitoring2024–2025
Google · USA
A model for health sounds: coughing, breathing, throat clearing. It provides features on top of which a researcher builds their own model and draws no conclusions about illness itself. It does not replace a doctor; decisions are made by a specialist. Voice recordings are personal data, so check the procedure with a lawyer.
- Features of cough and breathing sounds for your own model
- Research projects in health acoustics
- Selecting cough and breathing fragments from a recording
- Sizes
- a ViT-Large class model, trained on more than 300 million two-second clips
- Hardware
- from: Laptop
TextOllama2023–2025
Meta · USA
The models that started mass open source in AI. A huge ecosystem of fine-tuned versions and tools.
- Assistant for employees
- Summaries of meetings and documents
- Base for industry-specific fine-tuning
- Sizes
- 1B – 405B
- Hardware
- from: Laptop
Moderation and safetyOllama2023–2025
Meta · USA
Filter models that check chatbot requests and replies for dangerous topics against a list of categories. Version 4 also checks images. Russian is not officially supported.
- Checking user questions to the bot
- Checking bot replies before sending
- Reporting which rule category was violated
- Sizes
- 1B – 12B
- Hardware
- from: Laptop
Moderation and safety2023–2025
Falconsai and Freepik · USA and Spain
Small models that tell explicit images from regular ones. The Freepik model distinguishes four levels of explicitness. They run on a CPU.
- Filtering user photos and avatars
- Checking generated images before publishing
- Labeling a media library
- Sizes
- 86M
- Hardware
- from: Laptop
Moderation and safety2024–2025
Meta · USA
Tiny classifiers that catch attempts to hack a bot: prompt injections and rule bypassing. The 86M version is multilingual, 22M is English only.
- Protecting a bot from prompt injections
- Checking emails and documents that reach an AI agent
- Fast filter in front of a large model
- Sizes
- 22M – 86M
- Hardware
- from: Laptop
Image + textGGUF2024–2025
Hugging Face · France / USA
The smallest vision models from Hugging Face, starting at 256M; they run in a browser and on a phone. SmolVLM2 also understands video.
- Describing photos and video on low-end hardware
- Reading simple documents
- Embedding in mobile and offline apps
- Sizes
- 256M – 2.2B
- Hardware
- from: Laptop
Text to SQL2025
Alibaba · China
Alibaba models for turning questions into SQL, based on Qwen2.5-Coder. They work with different SQL dialects; a small 3B version suits modest hardware.
- Plain-language database questions
- Queries for different databases (PostgreSQL, MySQL, SQLite)
- Automating routine reports
- Sizes
- 3B – 32B
- Hardware
- from: Laptop
Drawings and CAD2024–2025
University of Luxembourg (SnT) and Artec3D · Luxembourg
Turns a point cloud of a part into executable CadQuery Python code, that is, a parametric 3D model you can open and edit in CAD. The output is a draft: an engineer checks and signs off the document.
- Recovering a parametric model from a 3D scan of a part
- Converting a point cloud into editable CadQuery code
- Preparing a draft model for a design engineer to finish
- Sizes
- 1.5B (Qwen2-1.5B plus a single projection layer)
- Hardware
- from: Laptop
Deepfake detection2025
Desklib · India
A recent open AI-text detector on DeBERTa-v3-large, trained on the RAID dataset, with a separate version for academic work. It errs in both directions - a human always reviews the result.
- Checking submitted articles and reports
- Filtering templated reviews and applications
- First-pass check of student work
- Sizes
- 0.4B (DeBERTa-v3-large)
- Hardware
- from: Laptop
Search and RAGRUOllama2024–2025
Nomic AI · USA
Fully open embeddings, with weights, data and training code. v2 is multilingual on MoE; there are versions for code and for searching PDF pages.
- Search across documents and a knowledge base
- Code search
- Search across scans and PDFs without text recognition
- Sizes
- 137M – 7B
- Hardware
- from: Laptop
Text to speechRUGGUF2023–2025
Rhasspy / Open Home Foundation · USA
Very fast speech synthesis that runs even on a Raspberry Pi. Ready-made voices in 35+ languages, including several Russian ones.
- Voicing notifications and bot replies
- Voice for offline devices
- Voice menus
- Sizes
- about 5M – 30M
- Hardware
- from: Laptop
Math and reasoningGGUF2025
Stanford University · USA
A reasoning model trained on just a thousand problems. It can be told to think longer to answer a hard question more accurately.
- Calculations and formula checks
- Working through complex problems step by step
- Training
- Sizes
- 1.5B – 32B
- Hardware
- from: Laptop
Moderation and safetyOllama2024–2025
Google · USA
Gemma-based filters: they check text for dangerous and offensive content, and ShieldGemma 2 checks images. Focused on English.
- Moderating user messages
- Checking bot replies
- Checking generated images before publishing
- Sizes
- 2B – 27B
- Hardware
- from: Laptop
Speech to textRUGGUF2022–2025
OpenAI · USA
Speech recognition in 99 languages, including Russian. The de facto standard for transcribing calls and meetings. Hugging Face's faster Distil-Whisper is English only.
- Transcription of calls and video meetings
- Video subtitles
- Voice messages to text
- Sizes
- 39M – 1,5B
- Hardware
- from: Laptop
Computer-use agents2024–2025
Salesforce · USA
Salesforce models for function calling and agents: they pick the right tool and fill in its parameters. Strong on benchmarks, but the license is non-commercial.
- Calling APIs and internal services on user request
- Multi-step agents with several tools
- Comparing approaches before choosing a commercial model
- Sizes
- 1B – 8x22B
- Hardware
- from: Laptop
Search and RAG2025
The authors of the CareerBERT paper, German universities · Germany
A German-language model that matches a resume to occupations from the European ESCO reference list and suggests suitable directions. A human makes the decision about a candidate; automatic screening without review must not be used.
- Suggesting occupations that fit the candidate experience
- Matching resumes against job descriptions
- Hints on internal career moves
- Sizes
- 110M
- Hardware
- from: Laptop
Plates and vehicles2023–2025
szad670401 (open project) · China
A well-known open system for Chinese plates: single-row blue and yellow plates, electric vehicles, driving-school cars. It has to be fine-tuned for the Russian plate format. Filming vehicles and people is personal data processing: agree the procedure with a lawyer.
- Plate recognition at entry and exit
- Running on modest hardware without a GPU
- Embedding recognition into your own application
- Sizes
- compact detection and reading models designed to run without a GPU
- Hardware
- from: Laptop
Text to speechGGUF2024–2025
hexgrad (independent developer) · not disclosed
A tiny speech synthesis model (82M) that sounds on par with large ones. Runs on a regular CPU; English and a few other languages, no Russian.
- Voicing articles and notifications
- Voice for apps without a GPU
- Bulk text voiceover
- Sizes
- 82M
- Hardware
- from: Laptop
Computer-use agents2024–2025
Microsoft · USA
Breaks a screenshot down into buttons, fields and icons with labels so a regular language model can understand and control the screen. It does not click itself; it serves as the agent's eyes.
- Mapping legacy software screens for automation
- Preparing an agent to work in an interface
- Checking that the required elements are on screen
- Sizes
- under 1B (detector + captioning)
- Hardware
- from: Laptop
Computer vision2023–2025
Google · USA
Models that map images and text into a shared space: you can search photos by words and classify images without training. OpenAI's CLIP (2021) is the predecessor.
- Image search by text query
- Automatic catalog labeling and tagging
- Filtering prohibited content
- Sizes
- about 0.2B to 2B
- Hardware
- from: Laptop
Photo editing2024–2025
Prama LLC · USA
A background removal model focused on difficult edges: hair, fur, fine details. The open version is MIT-licensed and can process video.
- Cutting out products and people from photos
- Background removal in video
- Preparing photos for a catalog
- Sizes
- about 95M
- Hardware
- from: Laptop
Search and RAGRU2023–2025
Alibaba · China
Alibaba embeddings and rerankers for search: from tiny to 7B based on Qwen2. There is a multilingual mGTE version with long context.
- Semantic search across documents
- Reranking search results
- Clustering and classifying texts
- Sizes
- 33M – 7B
- Hardware
- from: Laptop
Image + textGGUF2024–2025
DeepSeek · China
A single model that both understands images and draws them from a description. Janus-Pro-7B drew attention in early 2025, but its image quality is below specialised models.
- Answering questions about images
- Draft illustrations from a description
- Experiments with a unified vision and generation model
- Sizes
- 1B – 7B
- Hardware
- from: Laptop
Text analysisGGUF2024–2025
Answer.AI and LightOn · USA / France
A modern replacement for classic BERT: faster, reads up to 8 thousand tokens at once. A base for your own classifiers. Trained on English and code; for Russian there is RuModernBERT.
- Classifying requests and documents
- Finding relevant passages in long texts
- Base for your own classifier after fine-tuning
- Sizes
- 150M – 395M
- Hardware
- from: Laptop
Math and reasoningOllama2024–2025
Qwen (Alibaba) · China
Maths versions of Qwen: they solve problems step by step and can calculate via code. Includes reward models that check each step of a solution.
- Calculations and formula checks
- Checking calculations in estimates and reports
- Working through problems step by step
- Sizes
- 1.5B – 72B
- Hardware
- from: Laptop
Text analysisRUOllama2024–2025
Jina AI · Germany
Small models that turn raw web page HTML into clean Markdown or JSON. Handy for preparing websites for a knowledge base. Non-commercial license only.
- Cleaning website pages for a knowledge base
- Extracting data from pages into JSON
- Preparing texts for RAG
- Sizes
- 0.5B – 1.5B
- Hardware
- from: Laptop
Search and RAGRUOllama2019–2025
UKP Lab (TU Darmstadt), later Hugging Face · Germany
The classic for meaning-based search: small, fast models that run even on a modest server without a GPU. The multilingual versions understand Russian.
- Search across a knowledge base and FAQ
- Finding similar tickets and duplicates
- Grouping reviews and requests by topic
- Sizes
- about 20M – 470M
- Hardware
- from: Laptop
Computer vision2022–2025
University of Sydney and JD Explore Academy · Australia / China
A simple, accurate model for human pose estimation via keypoints. ViTPose++ handles human, animal and whole-body poses; built into the Transformers library.
- Body keypoints in photos and video
- Motion analysis in sports and rehabilitation
- Monitoring work postures and safety practices
- Sizes
- 33M – about 1B
- Hardware
- from: Laptop
Deepfake detection2024
Meta · USA
An imperceptible mark in synthetic speech plus a fast detector that finds it even inside a fragment of a long recording. The detector errs in both directions: a hit is a reason for a human to check, not proof.
- Marking speech synthesized by your service
- Finding your own mark in third-party publications
- Checking whether synthesis was mixed into a call recording
- Sizes
- a watermark generator and detector, 16-bit message
- Hardware
- from: Laptop
Search and RAG2024
TechWolf · Belgium
Finds mentions of skills in a vacancy or resume text and maps them to the company skill reference list. A human makes the decision about a candidate; automatic screening without review must not be used.
- Extracting skills from a job description
- Matching candidate skills against requirements
- Building a competence map across departments
- Sizes
- 109M
- Hardware
- from: Laptop
Fact-checking and judges2024
Patronus AI · USA
A small judge: it scores against your criteria and highlights which part of the answer led to that score. The license is non-commercial. The judge itself makes mistakes and does not replace manual review.
- Scoring answers against your criteria with an explanation
- Understanding why a score was lowered
- Bulk review of assistant conversations
- Sizes
- 3.8B (based on Phi-3.5-mini)
- Hardware
- from: Laptop
Music and sound2024
Tencent AI Lab · China
The MuQ music encoder and the MuQ-MuLan model, which matches music and text: you can search for tracks by a description in English or Chinese.
- Searching music by text description
- Tagging tracks by genre and mood
- Finding similar music
- Sizes
- 300M – 700M
- Hardware
- from: Laptop
Plates and vehiclesRU2022–2024
RIA.com · Ukraine
A plate recognition system with separate reading modules for Russia, Kazakhstan, Belarus, Ukraine, Georgia, Armenia and Kyrgyzstan. Filming vehicles and people and storing the records is personal data processing: agree the procedure with a lawyer.
- Reading a Russian plate from a camera
- Identifying the country and plate type
- Logging vehicles at entry and exit
- Sizes
- a YOLOv8 detector plus separate character-reading modules
- Hardware
- from: Laptop
Search and RAGRUOllama2024
Snowflake · USA
Snowflake embeddings built specifically for search. Version 2.0 is multilingual (Russian is on the language list), handles long texts up to 8K tokens and can compress vectors.
- Search across documents and knowledge bases
- Picking passages for RAG
- Search across reports and internal data
- Sizes
- 22M – 568M
- Hardware
- from: Laptop
TextRU2024
MTS AI (MWS AI) · Russia
A lightweight Russian-language model from MTS AI for Russian texts: answers, summaries, drafts. A ready version for CPU without a GPU is available. The larger Cotype Pro is not released openly.
- Drafts of emails and descriptions in Russian
- Short document summaries
- Answers to common customer questions
- Sizes
- 1.5B
- Hardware
- from: Laptop
Documents and OCR2024
StepFun · China
One of the first general-purpose new-generation OCR models: text, formulas, tables, sheet music and diagrams. Small and runs on low-end hardware, but already behind newer models.
- Recognising scanned invoices and contracts
- Converting tables into an editable format
- Recognising formulas and diagrams
- Sizes
- 580M
- Hardware
- from: Laptop
TranslationRU2024
deepvk (VK) · Russia
Compact Kazakh-Russian translators from VK. At 197M they translate as well as the 600M NLLB and run on a regular CPU.
- Translating requests from Kazakh to Russian
- Translating documents and instructions into Kazakh
- Bilingual customer support
- Sizes
- 197M
- Hardware
- from: Laptop
Recommenders2024
Marqo · Australia
Models that turn a product photo and its title into a single vector: suitable for a similar-items block, image search and matching by description. Built for retail product cards.
- Similar items by photo and title
- Catalogue search by image
- Product search from a shopper phrase
- Sizes
- 203M (B) и 652M (L)
- Hardware
- from: Laptop
CodeOllama2024
INF Technology · China
Fully reproducible coding models: along with the weights, the data, its cleaning pipeline and the training recipe are open. Understand English and Chinese.
- Code generation and completion
- Training your own coding model from an open recipe
- A programming assistant on low-end hardware
- Sizes
- 1.5B – 8B
- Hardware
- from: Laptop
Image + textGGUF2024
Google · USA
Google's vision model built on Gemma, designed as a base for fine-tuning on a narrow task: captions, object detection, reading text.
- Fine-tuning for your own recognition task
- Finding objects in photos
- Reading text in images
- Sizes
- 3B – 28B
- Hardware
- from: Laptop
Forecasting2024
IBM Research · USA
Tiny forecasting models from IBM: they run on an ordinary CPU and sit next to the business system without a separate GPU server.
- Forecasting sales and warehouse stock
- Forecasting energy use and equipment load
- Fast forecasts right on the company server
- Sizes
- very small: TinyTimeMixers have about 1M parameters
- Hardware
- from: Laptop
Forecasting2024
Auton Lab, Carnegie Mellon University · USA
A foundation model for numeric series: one engine is used for forecasting, anomaly detection, filling gaps and classification.
- Forecasting demand and load
- Detecting anomalies in sensor readings and metrics
- Filling gaps in historical data
- Sizes
- about 40M – 385M
- Hardware
- from: Laptop
Cybersecurity2024
cybersectony · not disclosed
A very light classifier for emails and links showing signs of phishing. It errs in both directions, so borderline emails are still reviewed by a person.
- Flagging suspicious incoming emails
- Checking links from correspondence before opening them
- A first-level filter in a mail gateway
- Sizes
- about 66M
- Hardware
- from: Laptop
Finance2024
MIT and MIT-IBM Watson AI Lab · USA
Models that label suspicious chains of transfers by looking at who sent the money at the start of the chain and who received it at the end. A human makes the decision on a disputed operation; automatic blocking without review is not acceptable.
- Classifying transfer chains as ordinary or needing review
- Finding new suspicious chains in a large flow of operations
- Preparing material for the compliance team
- Sizes
- checkpoints from 0.1 to 45 MB
- Hardware
- from: Laptop
Plates and vehicles2023–2024
dima806 (open project) · not disclosed
Two simple photo classifiers: vehicle type and car brand. Trained on public datasets, so check them on your own footage before use. Filming vehicles and people is personal data processing: agree the procedure with a lawyer.
- Identifying the vehicle type from a photo
- Pre-labelling the car brand
- Going through photos in listings and applications
- Sizes
- based on ViT-base (google/vit-base-patch16-224-in21k)
- Hardware
- from: Laptop
Recommenders2024
Recombee · Czechia
Description encoders trained so that items people actually buy together end up close to each other, not merely items that sound alike. Versions trained on public catalogues are published.
- A frequently-bought-together block
- Recommendations for listings with no sales history
- Moving the model to a new catalogue
- Sizes
- about 110M (built on all-mpnet-base-v2)
- Hardware
- from: Laptop
Cybersecurity2023–2024
Huawei and University of Science and Technology of China (LogAIBox project) · China
A model pretrained on a large volume of logs from different systems: it turns a log line into a vector on top of which failure and outlier detection is fine-tuned. A human makes the decision on a disputed operation; automatic blocking without review is not acceptable.
- Finding unusual entries in operation logs
- Grouping similar failure messages
- Preparing features for an in-house monitoring model
- Sizes
- about 110M (BERT-base architecture)
- Hardware
- from: Laptop
CodeOllama2023–2024
DeepSeek · China
DeepSeek's coding model family: from small autocompletion models to the large MoE V2, which matched closed models in 2024. Later, coding moved into DeepSeek's general models.
- Code autocompletion and generation
- Translating code between programming languages
- Finding bugs and explaining other people's code
- Sizes
- 1.3B – 236B-A21B
- Hardware
- from: Laptop
Fact-checking and judges2024
Flow AI · not disclosed
A small judge model: it checks an answer against your instruction and gives a score with an explanation. Fits on a modest server. The judge itself makes mistakes and does not replace manual review.
- Checking AI assistant answers against the instruction
- Bulk scoring of exported conversations
- Quality control before rolling out changes
- Sizes
- 3.8B (based on Phi-3.5-mini)
- Hardware
- from: Laptop
Moderation and safety2024
iiiorg · not disclosed
A popular detector of 17 types of personal data in six European languages. No Russian and a non-commercial license: suitable for trials and research.
- Finding personal data in texts
- Comparing the quality of PII detectors
- Sizes
- 278M
- Hardware
- from: Laptop
Forecasting2024
The Time-MoE team · not disclosed
A forecasting model with a sparse architecture: only part of the network runs at each step, so it stays fast at a small size.
- Forecasting sales and stock levels
- Forecasting load on services and staff
- Planning purchases from history
- Sizes
- 50M and 200M
- Hardware
- from: Laptop
CodeOllama2024
01.AI · China
Coding models from 01.AI at 1.5B and 9B with a 128K-token context and support for 52 programming languages. A separate line next to the text Yi models.
- Code autocompletion and generation
- Explaining and refactoring code
- A programming assistant without the cloud
- Sizes
- 1.5B – 9B
- Hardware
- from: Laptop
RecommendersNot maintained2024
HKUDS, University of Hong Kong · China
Encoders that put a text portrait of a shopper and a text description of an item into one vector space so they can be matched directly. They help where a new listing has no purchase statistics yet.
- Recommendations for new items with no statistics
- Matching by a text portrait of the shopper
- Reinforcing ordinary recommendations with descriptions
- Sizes
- three RoBERTa-based versions: small, base, large
- Hardware
- from: Laptop
Fact-checking and judgesOllamaNot maintained2024
UT Austin and Bespoke Labs · USA
Checks whether each claim in an AI answer is supported by the source documents. The small versions are free; the larger 7B is in Ollama but non-commercial.
- Checking RAG bot answers against documents
- Finding unsupported claims in reports and summaries
- Automated quality control of AI answers
- Sizes
- 0.4B – 7B
- Hardware
- from: Laptop
TextOllamaNot maintained2023–2024
Stability AI · UK
Small models from Stability AI: StableLM 2 (1.6B) knows 7 European languages, Stable Code (3B) completes code. No updates since 2024.
- A lightweight chatbot on an ordinary PC
- Code autocompletion in the editor
- A base for fine-tuning on your own task
- Sizes
- 1.6B – 12B
- Hardware
- from: Laptop
RerankersGGUFNot maintained2023–2024
BAAI (Beijing Academy of Artificial Intelligence) · China
Rerankers: they take passages found by search and reorder them by how well they actually match the question. v2-m3 is multilingual and lightweight, often paired with bge-m3.
- Refining search results before a chatbot answers
- Sorting knowledge base search results
- Selecting the most relevant clauses of contracts and policies
- Sizes
- 278M – 9B
- Hardware
- from: Laptop
RecommendersGGUFNot maintained2024
Ohio State University (NingLab) · USA
Three language models tuned on a large set of commerce instructions: product selection, answers from the item card, matching listings, review analysis. Your own assortment still needs fine-tuning.
- Finding a product from a shopper request
- Answering questions about an item card
- Matching identical listings across catalogues
- Sizes
- 2.7B – 13B
- Hardware
- from: Laptop
Fact-checking and judgesNot maintained2023–2024
Vectara · USA
A small model that checks whether an AI answer is grounded in the source text or made up. Runs on a CPU and works well as a filter in RAG systems.
- Checking knowledge base chatbot answers for fabrications
- Quality control of document summaries
- Comparing language models by their tendency to make errors
- Sizes
- 110M
- Hardware
- from: Laptop
Text analysisRUNot maintained2020–2024
SberDevices (ai-forever) · Russia
Sber's Russian-language encoders trained on large Russian corpora. A base for classifiers, NER and semantic search in Russian.
- Classifying requests in Russian
- Extracting names, amounts and dates after fine-tuning
- Detecting review sentiment
- Sizes
- about 30M to 430M
- Hardware
- from: Laptop
Image + textNot maintained2024
Microsoft · USA
A very small vision model: captions, object detection, segmentation and text reading from a single prompt. Runs even on a CPU.
- Reading text in photos
- Finding and highlighting objects
- Automatic photo captions
- Sizes
- 0.23B – 0.77B
- Hardware
- from: Laptop
Text analysisRUNot maintained2024
udmurtNLP · not disclosed
A project around the Udmurt language: encoders based on mBERT, rubert-tiny2 and Glot500, part-of-speech taggers, a typo correction model and Udmurt-English embeddings.
- Parsing Udmurt texts by part of speech
- Correcting typos and recognition errors
- Semantic search over Udmurt material
- Sizes
- 33M – 187M
- Hardware
- from: Laptop
RecommendersNot maintained2024
UC San Diego (McAuley Lab) · USA
Light encoders trained on pairs of item card and real review: they produce item vectors for similar-item blocks and for search by a shopper description. The weights are small and run on an ordinary server.
- A similar-items block based on descriptions
- Product search from a shopper phrase
- Suggesting cards for new listings
- Sizes
- 125M и 355M
- Hardware
- from: Laptop
Deepfake detectionNot maintained2024
UC Santa Barbara and co-authors · USA
A Longformer-based AI-text detector: it holds a long document whole and was trained on texts from many different language models. It errs in both directions; its output is a reason for a human to check.
- Checking long articles and reports as a whole
- Filtering machine text in a publication flow
- Comparing detectors on your own data
- Sizes
- about 150M (Longformer-base)
- Hardware
- from: Laptop
Text analysisRUNot maintained2023–2024
CIS, LMU Munich · Germany
Detects which language a text is written in: the third version covers more than two thousand labels, including Tatar, Bashkir, Chuvash, Udmurt, Mari, Erzya, Komi and other languages of Russia.
- Sorting mixed text archives by language
- Filtering out noise and foreign languages before training
- Routing requests to the right operator or model
- Sizes
- a FastText model; parameter count is not stated on the model card
- Hardware
- from: Laptop
Text to speechNot maintained2024
MyShell and MIT · USA
Lightweight multilingual speech synthesis that keeps up in real time on an ordinary CPU. English with accents, Spanish, French, Chinese, Japanese and Korean; no Russian.
- Voicing bot replies in foreign languages
- Voicing training materials
- Reading texts aloud on a server without a GPU
- Sizes
- small, runs in real time on a CPU
- Hardware
- from: Laptop
Text analysisNot maintained2024
University of Southern Denmark · Denmark
Turns a free-form occupation description into a standard HISCO code in 13 languages. Built for historical archives, but also useful for cleaning up job title reference lists. A human makes the decision about a candidate; automatic screening without review must not be used.
- Mapping mixed occupation names onto a single code
- Processing archives of HR and statistical data
- Preparing data for reporting
- Sizes
- based on CANINE-s, size not stated on the model card
- Hardware
- from: Laptop
Voice: speakers and soundNot maintained2024
MyShell and MIT · USA
Instant voice cloning from a short sample with control over emotion and accent; V2 speaks several languages. Use only with the voice owner's consent.
- Voicing videos with the company narrator's voice
- Voice bot with a recognizable brand voice
- Transferring timbre onto existing speech synthesis
- Sizes
- under 1B
- Hardware
- from: Laptop
CodeOllamaNot maintained2023–2024
BigCode (Hugging Face and ServiceNow) · USA / France
One of the first open coding models, trained on an open set of source code with an option to exclude your own repository. Today it is more a base for fine-tuning than a leader.
- Code autocompletion in the editor
- Fine-tuning on the company's internal code
- Generating boilerplate code and tests
- Sizes
- 1B – 15B
- Hardware
- from: Laptop
TextRUNot maintained2023–2024
Sber (ai-forever) · Russia
Sber's Russian text-to-text model, successor to ruT5 (2021). Small and fast: fine-tuned for summarizing, paraphrasing and fixing errors in Russian text; ready-made SAGE spell-checking versions exist.
- Fixing spelling mistakes and typos in Russian text
- Short summaries and paraphrasing
- Normalizing requests and inquiries before processing
- Sizes
- 95M – 1.7B
- Hardware
- from: Laptop
CybersecurityNot maintained2023–2024
SmartData@PoliTO, Politecnico di Torino · Italy
A pair of models from an Italian university: they read a recorded command session and mark which parts belong to reconnaissance, persistence and other attacker steps. A human makes the decision on a disputed operation; automatic blocking without review is not acceptable.
- Labelling command logs by stage of activity
- Grouping similar sessions for incident review
- Preparing features for server monitoring
- Sizes
- about 125M (based on CodeBERT)
- Hardware
- from: Laptop
TextOllamaNot maintained2023–2024
TinyLlama (SUTD researchers) · Singapore
A 1.1B model with the Llama 2 architecture, trained on 3 trillion tokens. Now behind newer small models, but still a popular base for experiments and fine-tuning.
- Simple chatbots on low-end hardware
- Experiments and team training
- A base for fine-tuning on a narrow task
- Sizes
- 1.1B
- Hardware
- from: Laptop
CybersecurityGGUFNot maintained2023–2024
ZySec AI · India
A small open assistant for security professionals: questions about standards, reviewing threats and vulnerabilities, drafting internal documents.
- Answering questions about security policies and standards
- First-pass review of threat reports
- Drafting internal protection guidelines
- Sizes
- 2.8B и 7B
- Hardware
- from: Laptop
Search and RAGRUNot maintained2022–2024
Microsoft · USA
Proven models for semantic search. The multilingual versions work well with Russian and are still a reliable base for RAG.
- Search across a knowledge base and documents
- Finding answers for a chatbot (RAG)
- Finding similar requests and duplicates
- Sizes
- 33M – 7B
- Hardware
- from: Laptop
ForecastingNot maintained2024
ServiceNow, Mila and partners · Canada
One of the first open out-of-the-box forecasting models. Tiny, gives a probabilistic forecast, now behind Chronos and TimesFM.
- Probabilistic sales forecast
- Quick forecasting pilots
- Baseline model for comparison
- Sizes
- 2.4M
- Hardware
- from: Laptop
Documents and OCRNot maintained2024
Microsoft · USA
One model for every document task: reading, answering questions about a page, extracting fields, classification. In HR it is used to parse resumes and attached scans. A human makes the decision about a candidate; automatic screening without review must not be used.
- Extracting fields from a resume and its attachments
- Answering questions about document content
- Classifying incoming documents
- Sizes
- 742M
- Hardware
- from: Laptop
Search and RAGRUOllamaNot maintained2024
BAAI · China
A model for meaning-based search in about a hundred languages. The core of RAG: the bot finds the right part of a document before answering.
- Search across a document base
- RAG for a chatbot
- Finding similar requests and duplicates
- Sizes
- 568M
- Hardware
- from: Laptop
RerankersNot maintained2023
NetEase Youdao · China
An embedding-plus-reranker pair for knowledge bases. The card lists English, Chinese, Japanese and Korean — Russian is not among the stated languages.
- Search across a knowledge base and reference materials
- Reordering retrieved passages
- Picking answers for a support chatbot
- Sizes
- about 280M
- Hardware
- from: Laptop
Photo editingNot maintained2023
Alibaba DAMO Academy · China
Colorizes black-and-white photos in natural colors. A lightweight model with a commercial-friendly license; a compact tiny version is available.
- Colorizing archival photos
- Color versions of historical photos for publications
- Family photo restoration service
- Sizes
- DDColor-T (tiny) and DDColor-L
- Hardware
- from: Laptop
Deepfake detectionNot maintained2023
Hello-SimpleAI · China
One of the first open AI-text classifiers, trained on the HC3 corpus of paired human and ChatGPT answers. It errs in both directions: its output is a reason to talk to the author, not proof.
- First-pass check of student work
- Filtering templated applications and reviews
- Flagging suspicious texts for manual review
- Sizes
- about 125M (RoBERTa-base)
- Hardware
- from: Laptop
Text analysisNot maintained2022–2023
Mike Zhang, Rob van der Goot, Barbara Plank (IT University of Copenhagen and LMU Munich) · Denmark
A research line of models for labour market texts: trained on job postings and the European ESCO occupation taxonomy, they pull skills and requirements out of vacancies. A human makes the decision about a candidate; automatic screening without review must not be used.
- Extracting skills and requirements from vacancy text
- Mapping skills to the single ESCO reference list
- Classifying vacancies and job titles
- Sizes
- 110M – 560M
- Hardware
- from: Laptop
TranslationRUGGUFNot maintained2023
Google · USA
Google's translator for more than 400 languages under a permissive license. Russian is supported. A good substitute for NLLB when commercial use is needed.
- Translating documents and emails
- Translating catalogs and product descriptions
- Translating into CIS and Asian languages
- Sizes
- 3B – 10B
- Hardware
- from: Laptop
Text to speechNot maintained2023
Columbia University · USA
A lightweight English speech synthesis model with natural intonation. Many other models, such as Kokoro, are built on it.
- Voicing texts in English
- A base for fine-tuning your own voice
- Voice service prototypes
- Sizes
- about 150M
- Hardware
- from: Laptop
Documents and OCRNot maintained2022–2023
Microsoft · USA
Small models that find tables on PDF and scanned pages and restore their structure: rows, columns, headers. The text inside is read by a separate OCR.
- Finding tables in reports, statements and invoices
- Restoring rows and columns for export to Excel
- Preparing tabular data for analysis and RAG
- Sizes
- 29M
- Hardware
- from: Laptop
Music and soundNot maintained2023
LAION · Germany
CLIP for audio: maps audio and text into a shared space. Lets you search sounds and music by description and classify them without training. Text must be in English.
- Search sounds and music by description
- Automatic tags for an audio library
- Recognizing sound types (siren, breaking glass, voice)
- Sizes
- size not stated on the model card
- Hardware
- from: Laptop
Text to SQLNot maintained2023
RUCKBReasoning, Renmin University of China · China
An early line of open text-to-SQL models starting at 1B, including variants fine-tuned for specific database schemas.
- Turning an employee question into an SQL query
- Drafting warehouse queries for a report
- Embedding into a BI dashboard as a helper
- Sizes
- 1B – 15B
- Hardware
- from: Laptop
Text to speechRUNot maintained2023
Coqui · Germany
A popular model for cloning a voice from a short sample in 17 languages, including Russian. Coqui has shut down and development has stopped.
- Voice cloning from a sample
- Multilingual voiceover
- Research and prototypes
- Sizes
- about 470M
- Hardware
- from: Laptop
Photo editingNot maintained2022–2023
Taehoon Kim (POSTECH) · South Korea
A salient object detection model and the ready-made transparent-background tool built on it: removes backgrounds from photos, video and webcam with one command.
- Batch background removal from photos
- Replacing the background with a color or blur
- Background removal in video
- Sizes
- small (based on Swin-B)
- Hardware
- from: Laptop
Speech to textRUNot maintained2023
Meta AI · USA
Meta speech models covering more than a thousand languages. The supported list includes Bashkir, Tatar, Chuvash, Sakha, Ossetian, Chechen, Avar, Udmurt, Mari, Erzya, Moksha, Kalmyk and Karelian. Quality varies a lot by language, so test it on your own recordings.
- Transcribing audio and video in rare languages
- Reading text aloud in a national language
- Detecting which language a recording is in
- Sizes
- 300M – 1B
- Hardware
- from: Laptop
Documents and OCRNot maintained2023
Meta · USA
An early model that converts scientific PDFs into text with formulas. Now outdated and outperformed by almost all modern OCR models.
- Converting scientific papers from PDF into text with formulas
- Digitising technical documentation
- Sizes
- 250M – 350M
- Hardware
- from: Laptop
Deepfake detectionNot maintained2022–2023
EURECOM · France
A step beyond AASIST: instead of raw audio it uses the wav2vec 2.0 speech encoder, which helps it hold up on unfamiliar synthesis methods. It errs in both directions - a human reviews the result.
- Spotting synthetic speech in calls
- Checking voice messages and recordings
- Fine-tuning for your own data and codecs
- Sizes
- about 0.3B (wav2vec 2.0 XLS-R encoder)
- Hardware
- from: Laptop
Voice: speakers and soundNot maintained2022–2023
Hendrik Schröter (University of Erlangen) · Germany
Lightweight real-time speech noise suppression that works even on a regular CPU and low-power devices. Removes hum, street and office noise while keeping the voice.
- Cleaning calls and voice messages of noise
- Preparing recordings before speech recognition
- Noise suppression for video calls
- Sizes
- about 2M
- Hardware
- from: Laptop
Photo editingNot maintained2022–2023
XPixel Group (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, and others) · China
Transformer-based photo upscaling, more accurate than SwinIR on fine details. Versions for real noisy photos and a lightweight HAT-S.
- Upscaling product and interior photos
- Preparing images for print
- Sharpening archival photos
- Sizes
- 9M – 40M
- Hardware
- from: Laptop
TextRUGGUFNot maintained2022–2023
Sber (ai-forever) · Russia
Sber's multilingual model covering 61 languages, including languages of the peoples of Russia and the CIS. Separate fine-tunes exist for Buryat, Yakut, Tatar, Bashkir, Kazakh and others, rare for open models.
- Texts in languages of the peoples of Russia and the CIS
- Base for fine-tuning on a less common language
- Drafts and templates in several languages
- Sizes
- 1.3B – 13B
- Hardware
- from: Laptop
TextRUGGUFNot maintained2023
SberDevices (ai-forever) · Russia
Separate mGPT versions, one per language: Bashkir, Buryat, Kalmyk, Mari, Ossetian, Tatar, Tuvan, Chuvash and Sakha. Each card also lists Russian and English.
- Generating and continuing text in a national language
- A base for fine-tuning to your own task
- Experiments with rare languages without training from scratch
- Sizes
- 1.3B
- Hardware
- from: Laptop
CybersecurityNot maintained2022–2023
Ehsan Aghaei and co-authors · USA
A compact language encoder trained on cybersecurity texts: tagging threat reports, finding entities and classification.
- Tagging threat reports and vulnerability bulletins
- Extracting entities from security texts
- Classifying and searching an internal incident base
- Sizes
- около 125M
- Hardware
- from: Laptop
Text to speechRUGGUFNot maintained2023
Suno · USA
One of the first open models to voice text with intonation, laughter and pauses. Supports about ten languages, including Russian. Now outdated.
- Draft voiceovers for videos
- Voice service prototypes
- Sound effects in speech
- Sizes
- about 300M – 1B
- Hardware
- from: Laptop
Weather and climateNot maintained2023
Huawei Cloud · China
One of the first weather neural networks, published in Nature and added to ECMWF charts. The weights are open for research only; commercial use is prohibited.
- Research weather forecasts a week ahead
- Comparison with other weather models on your own data
- Training courses on weather neural networks
- Sizes
- 4 models of ~1.1 GB each (1, 3, 6 and 24-hour steps)
- Hardware
- from: Laptop
Drawings and CADNot maintained2023
Google Research · USA
Small models that turn an image of a chart or diagram into a table of numbers and answer questions about it. Values read off an image are approximate, so the result has to be checked.
- Turning a chart from a report or PDF into a table
- Natural-language questions about a diagram
- A short text description of a chart
- Sizes
- 282M
- Hardware
- from: Laptop
Text to SQLGGUFNot maintained2023
Numbers Station · USA
One of the first open text-to-SQL lines, including very small versions from 350M that run on an ordinary PC.
- Turning a question into SQL from a table description
- Hints while writing queries
- A local analyst helper with no data leaving the company
- Sizes
- 350M – 7B
- Hardware
- from: Laptop
Text analysisRUNot maintained2022–2023
David Dale (cointegrated) and the community · Russia
Ready-made tiny rubert-tiny models for Russian text: detect rudeness and insults, sentiment and emotions. They run on a CPU in milliseconds.
- Filtering insults in Russian chats and comments
- Labeling reviews as positive, neutral or negative
- Spotting irritated customers in requests
- Sizes
- 12M – 29M
- Hardware
- from: Laptop
Photo editingNot maintained2022–2023
S-Lab, Nanyang Technological University · Singapore
Popular face restoration for old and blurry photos; also works on video. Has face inpainting and colorization modes. Non-commercial license.
- Restoring faces in old photos
- Enhancing faces in low-quality video
- Family archive restoration pilots
- Sizes
- small, up to 0.1B
- Hardware
- from: Laptop
RecommendersNot maintained2023
FashionCLIP research project (Farfetch data) · not disclosed
A time-tested model for clothing and footwear: it places an item photo and its description in one space, so it fits similar-item blocks and outfit matching. Fine-tuning for your own assortment is advisable.
- Similar items by photograph
- Building an outfit and matching add-ons
- Automatic tagging of clothing cards
- Sizes
- built on CLIP ViT-B/32
- Hardware
- from: Laptop
TextNot maintained2022–2023
Google · USA
Compact input-output models trained to follow instructions. Still used as a cheap base for classification, extraction and short answers.
- Classification of requests and documents
- Extracting fields from text
- Short answers and summaries
- Sizes
- 80M – 20B
- Hardware
- from: Laptop
TranslationRUGGUFNot maintained2022–2023
Meta · USA
A translator for 200 languages, including rare and minor ones. Russian is supported. Strong language coverage, but the license prohibits commercial use.
- Translating texts between 200 languages
- Translating into rare languages where no other models exist
- Comparing quality when choosing a translator
- Sizes
- 600M to 3.3B (plus 54B MoE)
- Hardware
- from: Laptop
Image + textNot maintained2023
Google · USA
Reads a document or a screenshot as an image and answers with structure: text, fields, answers to questions. In HR it is fine-tuned for resumes and forms. A human makes the decision about a candidate; automatic screening without review must not be used.
- Extracting data from resumes and forms supplied as images
- Questions about the content of a scan
- Parsing tables and diagrams in documents
- Sizes
- 282M – 1.3B
- Hardware
- from: Laptop
TextNot maintained2022–2023
EleutherAI · USA
Fully open models from the non-profit lab EleutherAI: GPT-NeoX-20B and the Pythia series with published intermediate training checkpoints.
- Base model for fine-tuning
- Research into model behavior
- Simple text generation and completion
- Sizes
- 70M – 20B
- Hardware
- from: Laptop
Acoustic monitoringNot maintained2022
Microsoft · USA
A self-supervised sound understanding model that became the base for many current systems: teams take it as a starting point and fine-tune it on their own equipment sounds. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.
- A base for your own sound understanding model
- Audio features for spotting abnormal operating modes
- Labelling sound events on a site
- Sizes
- a ViT-base class model, around 90M parameters
- Hardware
- from: Laptop
TextNot maintained2022
Meta · USA
An early open Meta series matching GPT-3 in size. Outdated; useful for research and comparison.
- Research experiments
- Training specialists
- Comparison with modern models
- Sizes
- 125M – 66B (175B on request)
- Hardware
- from: Laptop
RecommendersNot maintained2022
Rutgers University · USA
An early and still popular approach where recommendations are expressed as plain text: one small engine handles selection, rating and explanation. Checkpoints are trained on public datasets; a store needs its own.
- Suggesting the next item from history
- Predicting an item rating
- A text explanation of a recommendation
- Sizes
- small and base versions built on T5
- Hardware
- from: Laptop
Music and soundNot maintained2022
MIT · USA
A classic 2021 sound recognition model: detects 527 AudioSet event classes (siren, barking, breaking glass, music). Lightweight, runs without a GPU, in Transformers since 2022.
- Sound event recognition
- Tagging an audio archive
- Detecting alarm sounds
- Sizes
- about 87M
- Hardware
- from: Laptop
TextGGUFNot maintained2022
BigScience (Hugging Face and the community) · France
One of the first large open models, trained by a community of hundreds of researchers in 46 languages. Today it is interesting mostly as a historical milestone.
- Text generation and translation in many languages
- Experiments and team training
- Base model for fine-tuning on a narrow task
- Sizes
- 560M – 176B
- Hardware
- from: Laptop
Documents and OCRNot maintained2022
SCUT DLVC Lab, South China University of Technology · China
A light model that takes both the text and the position of blocks on the page into account: trained in one language and transferable to others. Good for tagging fields in resumes and forms. A human makes the decision about a candidate; automatic screening without review must not be used.
- Tagging fields in resumes and forms
- Extracting data from forms and templates
- Parsing documents in several languages
- Sizes
- about 130M for the English version and about 280M for the multilingual one
- Hardware
- from: Laptop
Documents and OCRNot maintained2021–2022
Microsoft · USA
Recognizes a single line of text, including handwriting. The official weights are English only, but the model is often fine-tuned for other languages; there are community Russian versions.
- Recognizing handwritten lines in questionnaires and forms
- Recognizing printed lines after text detection on the page
- A base for fine-tuning to your own handwriting or font
- Sizes
- 62M – 608M
- Hardware
- from: Laptop
Documents and OCRNot maintained2022
NAVER CLOVA · South Korea
Reads a scanned document and returns a filled-in field structure straight away, with no separate OCR step. In HR it is fine-tuned for parsing resumes and forms. A human makes the decision about a candidate; automatic screening without review must not be used.
- Extracting fields from forms and resumes
- Parsing scans of certificates and diplomas
- Detecting the type of an incoming document
- Sizes
- about 200M
- Hardware
- from: Laptop
Text analysisNot maintained2020–2022
Microsoft · USA
Classic document understanding models: they take into account the text, its position on the page and the image. They are fine-tuned to extract fields from forms and receipts. Only the first version is free for commercial use.
- Extracting fields from questionnaires, forms and receipts after fine-tuning
- Classifying document types
- Answering questions about a scanned page
- Sizes
- about 110M – 370M
- Hardware
- from: Laptop
RerankersRUNot maintained2022
UKP Lab and the Sentence Transformers community · Germany
The most downloaded open rerankers: a tiny model reads a question-passage pair and scores how well they match. The multilingual mMARCO version covers Russian.
- Reordering knowledge base search results
- Selecting passages before a chatbot answers
- Finding duplicates among tickets and product cards
- Sizes
- about 4M – 120M
- Hardware
- from: Laptop
Computer visionNot maintained2021–2022
OpenAI · USA
The 2021 model that first linked images and text: search photos by words and classify them without training. English only; SigLIP 2 or PE are usually chosen today.
- Image search by text query
- Automatic tags for a catalog
- Finding similar images
- Sizes
- about 0.15B – 0.6B
- Hardware
- from: Laptop
Photo editingGGUFNot maintained2021–2022
Tencent ARC Lab · China
The classic for upscaling photos 2–4x while cleaning noise and compression artifacts. Lightweight, runs even on a CPU. Versions for drawings and anime.
- Upscaling old and small product photos
- Cleaning images of compression artifacts
- Preparing images for print
- Sizes
- about 17M
- Hardware
- from: Laptop
Computer visionNot maintained2022
Microsoft · USA
From an image it works out what kind of document it is: resume, diploma, certificate, contract. Helps sort candidate file bundles by type. A human makes the decision about a candidate; automatic screening without review must not be used.
- Sorting incoming candidate documents by type
- Checking that a document package is complete
- Finding the right scan in an archive
- Sizes
- base and large versions
- Hardware
- from: Laptop
Photo editingNot maintained2021–2022
Tencent ARC Lab · China
Proven face restoration for old and compressed photos, with a commercial-friendly license. Often paired with Real-ESRGAN; the most used versions are 1.3 and 1.4.
- Restoring faces in old photos
- Enhancing avatars and profile photos
- Restoration in a photo shop or online service
- Sizes
- small, up to 0.1B
- Hardware
- from: Laptop
Computer visionRUNot maintained2022
Sber AI and SberDevices (ai-forever) · Russia
A Russian version of CLIP: matches images with Russian captions. Lets you search photos by description and sort images into categories without training.
- Product search by photo and by Russian description
- Sorting images into categories without labeling
- Checking that a photo matches its caption
- Sizes
- 150M – 430M
- Hardware
- from: Laptop
Text analysisRUNot maintained2019–2022
Meta · USA
A classic multilingual encoder for 100 languages, including Russian. The base of many sentiment, NER and embedding models, including BGE-M3.
- Detecting review sentiment in different languages
- Extracting names and organizations after fine-tuning
- Classifying requests
- Sizes
- 270M – 10.7B
- Hardware
- from: Laptop
Deepfake detectionNot maintained2021
NAVER Clova AI Research and EURECOM · South Korea
The baseline open model against voice spoofing: it listens to the raw recording and tells a live person from synthesis or a replay. It errs in both directions - its output is a reason for a human to check, not proof.
- Voice check during phone authentication
- Filtering replays and synthesis in a voice menu
- A baseline when comparing voice detectors
- Sizes
- weight files of 0.4 and 1.3 MB
- Hardware
- from: Laptop
Text analysisRUNot maintained2021
Microsoft · USA
A time-tested encoder behind many classifiers and NER models (including GLiNER). The multilingual mDeBERTa-v3 understands Russian.
- Classifying review sentiment
- Entity extraction after fine-tuning
- Checking whether a conclusion follows from a text
- Sizes
- 70M – 435M
- Hardware
- from: Laptop
Text analysisRUNot maintained2021
David Dale (cointegrated) · Russia
A very small Russian-English BERT that runs fast on a regular CPU. Ready-made fine-tuned versions exist for sentiment, toxicity and emotions.
- Detecting review sentiment
- Filtering rude chat messages
- Fast classification of requests
- Sizes
- 12M – 29M
- Hardware
- from: Laptop
Photo editingGGUFNot maintained2021
Samsung AI Center Moscow (with Skoltech) · Russia
Removes unwanted objects, text and watermarks from photos with clean background fill. Lightweight and fast; still the standard for this task.
- Removing price tags, people and clutter from photos
- Cleaning interior and real estate photos
- Removing text and dates from archival photos
- Sizes
- about 51M
- Hardware
- from: Laptop
Photo editingNot maintained2021
ETH Zurich · Switzerland
A transformer model for upscaling, denoising and removing JPEG artifacts from photos. Lightweight and proven; often embedded in other systems.
- Photo upscaling
- Image denoising
- Removing compression artifacts
- Sizes
- about 12M
- Hardware
- from: Laptop
TranslationRUGGUFNot maintained2020–2021
Meta · USA
An early Meta translator that translates directly between 100 languages, without English in the middle. Russian is supported. Old, but light and permissively licensed.
- Translation between any pair of 100 languages
- Quick draft translation on modest hardware
- Base for fine-tuning to your subject area
- Sizes
- 418M – 12B
- Hardware
- from: Laptop
FinanceNot maintained2020
Prosus · Netherlands
A classic model that determines the tone of financial news: positive, negative or neutral. English only, runs fast on a CPU.
- Scoring the tone of company news
- Labeling reports and press releases
- Signals for analytics dashboards
- Sizes
- 110M
- Hardware
- from: Laptop
Deepfake detectionNot maintained2020
MiniVision Technology · China
Practically the only fully open weight set for single-frame face liveness: it tells a live person from a photo, a screen or a mask. It errs in both directions - a person must be able to appeal a rejection.
- Liveness check when signing in by selfie
- Protecting an access system from a photo on a phone
- A check during remote customer identification
- Sizes
- two models of about 1.8 MB each
- Hardware
- from: Laptop
