AI models that run on a laptop

HuatuoGPT

A large family of medical models: chat, an imaging version, the reasoning HuatuoGPT-o1 and the new HuatuoGPT-3 on Qwen3. Does not replace a doctor; decisions are made by a specialist.

• Draft discharge summaries for a doctor to review
• Searching medical literature
• Hints for doctors when reviewing images (Vision)

Sizes

7B – 72B

Hardware

from: Laptop

VibeVoice

Microsoft speech models: long multi-voice dialogue synthesis, fast synthesis for live conversation, and recognition of long recordings split by speaker, including in Russian.

• Transcribing long meetings with speaker labels
• Voicing podcasts and dialogues
• Real-time voice for assistants

Sizes

0.5B – 9B

Hardware

from: Laptop

DeepSeek

DeepSeek's flagship line: from the first 7B/67B to V4-Pro with 1.6 trillion parameters. Closed-model quality under an open MIT license; V4-Flash-Vision-Exp and V4.1-Flash understand images, context up to 1M tokens.

• Employee assistant on your own server
• Analysis of long contracts and reports
• Agents that work with tools and APIs

Sizes

7B – 1.6T-A49B

Hardware

from: Laptop

InternLM / Intern-S

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

MiMo

Xiaomi models for reasoning and agents: from the compact MiMo-7B to MiMo-V2.6-Pro with 1.02 trillion parameters. The larger versions understand text, images, video and audio, with a 1M token context. Languages: English and Chinese.

• Logic and calculation tasks
• Agents with tools
• Help for developers

Sizes

7B – 1,02T-A42B

Hardware

from: Laptop

GigaChat

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

YandexGPT / AliceAI

Yandex models trained from scratch with a focus on the Russian language and Russian context. The new AliceAI-Foundation 80B-A3B (Apache 2.0) is a base model only, with no instruct version: you fine-tune it for your own tasks. The efficient AliceAI-T5 35B-A0.6B is also available.

• Russian-language assistant and chatbot
• Answers based on the company knowledge base
• Base for industry-specific fine-tuning

Sizes

8B – 100B

Hardware

from: Laptop

Aya

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

TabPFN

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

Mitra

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

TabDPT

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

LimiX

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

InsightFace

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

MiniCPM

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

K2 (K2-Think, K2-V2, K2-Horizon)

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

DUSt3R / MASt3R

The family that started "single-pass" 3D reconstruction from a pair or set of photos without camera calibration. MASt3R added point matching and scale; MUSt3R and BLASt3R added video support.

• 3D scene from several photos without calibration
• Point matching between images
• Mapping from video (SLAM)

Sizes

0.57B – 0.69B

Hardware

from: Laptop

MERT

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

comma.ai openpilot (supercombo)

An open driver assistance system: a neural network keeps the lane and controls speed from a camera, plus a driver attention monitoring model. The models live right in the repository and are updated constantly.

• A research testbed for driver assistance systems
• Studying driver attention monitoring with an in-cabin camera
• Comparison with your own lane-keeping algorithms

Sizes

compact, designed for an in-vehicle device

Hardware

from: Laptop

Zarya (ai-forever)

A Russian and English research prototype: the model writes text in blocks at once (diffusion) rather than word by word, which speeds up responses. The authors do not recommend it for production systems.

• Experiments with faster generation
• Fine-tuning small models for your own tasks
• Research

Sizes

0.6B – 4B

Hardware

from: Laptop

Samsone

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

TrustMark

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

Qwen

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

MoGe

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

FRIDA / Giga-Embeddings

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

TimesFM

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

Moonshine

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

Granite Speech

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

IndexTTS

Speech synthesis with voice cloning and precise duration control, handy for video dubbing. Controls emotion separately from timbre.

• Video dubbing matched to timing
• Voice cloning
• Emotional voiceover

Sizes

about 1B – 2B

Hardware

from: Laptop

GLM (ChatGLM)

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

Hunyuan / Hy

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

Ling / Ring

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.

• Corporate assistant
• Agents for office processes
• Financial analytics (Fin version available)

Sizes

7.9B-A1.3B – 1T

Hardware

from: Laptop

Cohere Command

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

NVIDIA Nemotron

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).

• Agents with tool calling
• Reasoning and calculation tasks
• Answers based on long documents

Sizes

4B – 550B-A55B

Hardware

from: Laptop

IBM Granite

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

Liquid LFM

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.

• Offline assistant on a laptop or phone
• Data extraction from documents
• Tool calling in apps

Sizes

230M – 24B-A2B

Hardware

from: Laptop

GLiNER

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

TeleOCR

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

UVR / MDX-Net / RoFormer (разделение звука)

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

UI-Venus

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.

• Automating actions in mobile apps
• Filling in forms in web interfaces
• UI autotests

Sizes

2B – 72B

Hardware

from: Laptop

Community Forensics

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

UniversalFakeDetect

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

Mistral

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

NVIDIA Nemotron Embed

NVIDIA embeddings for search and RAG. Nemotron-3-Embed, released in 2026, is under the permissive OpenMDW license and works in many languages.

• Search across corporate documents
• RAG for chatbots and assistants
• Search across images and pages (VL versions)

Sizes

1B – 8B

Hardware

from: Laptop

GigaAM

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

LongCat

Models from Meituan, China's largest delivery service. LongCat-Flash adjusts compute to query complexity; LongCat-2.0 has 1.6 trillion parameters under MIT. Omni models (Flash-Omni, Next) and AudioDiT speech synthesis too.

• Agents for orders and service processes
• Corporate assistant
• Analysis of long documents

Sizes

1B – 1.6T-A48B

Hardware

from: Laptop

EXAONE

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

Kanana

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

T-Pro / T-Lite

T-Bank models fine-tuned from Qwen for Russian: they write and reason in Russian noticeably better than the original. T-Lite is 8B, T-Pro 32B on one GPU; T-Search is a multi-step search agent in Russian and English.

• Russian-language support chatbot
• Analysis of requests and documents in Russian
• Answers based on the company knowledge base

Sizes

7B – 36B-A3B

Hardware

from: Laptop

Apertus

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

Ovis

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

HunyuanOCR

A lightweight OCR model from Tencent: document parsing, finding text in photos, field extraction and translating text from images. Version 1.5 is faster and runs on an ordinary PC.

• Extracting fields from invoices and delivery notes
• Recognising tables and formulas
• Translating text in photos and scans

Sizes

1B

Hardware

from: Laptop

WeSpeaker

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

Demucs

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

RVC (Retrieval-based Voice Conversion)

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

Fara

Small Microsoft models for working in the browser: they look at the page and click, type and scroll. Designed to run directly on a work computer without the cloud.

• Filling in web forms and applications
• Collecting data from web portals without an API
• Checking websites against scenarios

Sizes

4B – 27B

Hardware

from: Laptop

EXAONE Tabular

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

Surya OCR

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; Russian scored 88.8% in benchmarks.

• 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

Jina Reranker

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

R3 (R3-Embedding и R3-Rerank)

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

Gemma

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

Mellum

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.

• 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

OpenThinker

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

RF-DETR

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

TiRex

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

Qwen3-ASR

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

Cohere Transcribe

Cohere's speech recognition model for 14 languages (Russian is not on the list), with a separate version for Arabic. Built for accurate transcription of business recordings.

• Transcribing meetings and interviews
• Subtitles
• Searching an audio archive

Sizes

2B

Hardware

from: Laptop

Zonos

Speech synthesis with voice cloning and fine control over emotion, speed and pitch.

• Voice cloning
• Emotional voiceover
• Voicing videos

Sizes

about 1.6B

Hardware

from: Laptop

ACE-Step

Fast generation of songs with vocals in 19 languages, including Russian: a full song in seconds, editing of individual parts and style changes.

• Songs and jingles for ads
• Background music for videos
• Demo versions of tracks

Sizes

about 2B – 4B

Hardware

from: Laptop

GLiNER-PII

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

Moondream

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

Unlimited-OCR

Baidu's OCR model building on DeepSeek-OCR ideas: processes multi-page documents and PDFs in a single pass and outputs structured text. Claimed to be multilingual, but the language list is not published.

• Converting multi-page PDFs and scans to text and Markdown
• Recognizing contracts, invoices and reports
• Preparing document archives for search and RAG

Sizes

3.3B

Hardware

from: Laptop

PP-OCR и PP-DocLayout (классический PaddleOCR)

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

InternVideo

A family of video models: encoders for search and classification of clips, and chat models that analyze long videos. InternVideo 3 is designed for multi-hour recordings.

• Searching a video archive with a text query
• Action recognition in video
• Answering questions about a long recording

Sizes

small encoders – 9B

Hardware

from: Laptop

Ai2 OlmoEarth

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

Meditron

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

TripoSR / TripoSG

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

Jina Embeddings

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

Dolphin

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

NVIDIA Parakeet / Canary / Nemotron Speech

Fast NVIDIA speech recognition models, including streaming ones for real-time use. Parakeet TDT v3 and Nemotron 3.5 ASR understand Russian.

• Transcribing calls and meetings
• Video subtitles
• Real-time voice input

Sizes

110M – 2.5B

Hardware

from: Laptop

Chatterbox

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

MOSS-TTS / MOSS-TTSD

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

Stable Audio

Generates short music clips and sound effects from a description. Version 3 is split into separate models for music and for sounds.

• Sound effects for videos and games
• Background music and jingles
• Interface sounds

Sizes

about 0.5B – 2.3B

Hardware

from: Laptop

Hunyuan-MT / Hy-MT

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

Aegis / Nemotron Safety Guard

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

BRIA RMBG

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

LLaVA

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

MiniCPM-V

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.

• On-device text recognition in photos
• Processing receipts and documents without sending them to the cloud
• Describing photos and video

Sizes

1.3B – 8B

Hardware

from: Laptop

Keye-VL

Vision models from Kuaishou focused on short videos. Keye-VL-2.0 (30B, 3B active) understands well what happens in a clip and when.

• Analysing and describing short videos
• Reviewing clips and content
• Finding the right moment in a video

Sizes

8B – 671B-A37B

Hardware

from: Laptop

PaddleOCR-VL

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

MinerU

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

Holo

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

Supertonic

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

Sapiens

Meta's models for analyzing people in photos: pose keypoints, body part segmentation, normals and depth. Sapiens2 was trained at high resolution and adds human matting.

• Pose and body keypoint detection
• Segmentation of body parts and clothing
• Separating a person from the background

Sizes

0.1B – 5B

Hardware

from: Laptop

ESM (ESM-2, ESM3, ESM C, ESMFold2)

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

Llama Nemotron Rerank

A small 1B reranker from NVIDIA. The vl version also takes document pages as images, not just text. The card states multilingual support without listing the languages.

• Reordering passages before an AI assistant answers
• Sorting retrieved scan and PDF pages
• Search across internal policies and instructions

Sizes

1B

Hardware

from: Laptop

Timer (THUML)

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

Granite Embedding

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

Toto

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

VoxCPM

Speech synthesis with voice cloning and natural intonation. VoxCPM2 supports 30 languages, including Russian.

• Voice cloning
• Voicing videos and audiobooks
• Voice for an assistant

Sizes

0.5B – 2.3B

Hardware

from: Laptop

ERNIE 4.5

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

Arcee Trinity

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

OPUS-MT (MarianMT)

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

Granite Guardian

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

OpenAI Privacy Filter

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

Granite Vision

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

ShowUI

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

NuExtract

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

Kyutai STT, TTS и Pocket TTS

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

Apriel

ServiceNow 15B models with step-by-step reasoning that fit on a single GPU. From version 1.5 they also understand images and are good at calling tools.

• A reasoning assistant for internal services
• Tool calling and enterprise agents
• Analysing screenshots and documents with images

Sizes

5B – 15B

Hardware

from: Laptop

Rnj-1

An 8B model trained from scratch by the company of one of the authors of the transformer architecture. Strong at code and technical tasks; version 1.5 handles context up to 160K tokens.

• Writing and fixing code
• A developer agent on a single GPU
• Solving technical and scientific problems

Sizes

8B

Hardware

from: Laptop

Audio Flamingo

Models that listen to speech, sounds and music and answer questions about them. Audio Flamingo Next handles recordings up to 30 minutes. Research use only.

• Detailed descriptions of audio recordings
• Questions and answers about a long recording
• Tagging music and sounds

Sizes

0.5B – 8B

Hardware

from: Laptop

Octen Embedding

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

POLLUX Judge (ai-forever)

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

Meno (Иван Бондаренко)

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

Segment Anything (SAM)

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

Hulu-Med

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

Goedel-Prover

Open models for formal proofs in Lean 4 from Princeton. The new Goedel-Code-Prover proves program correctness.

• Formal verification of mathematical workings
• Verifying code correctness
• Training

Sizes

7B – 32B

Hardware

from: Laptop

pplx-embed

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 – 4B

Hardware

from: Laptop

Voxtral

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 is also available.

• Transcribing and summarizing recordings
• Asking questions about audio
• Real-time recognition

Sizes

3B – 24B

Hardware

from: Laptop

Fish Speech / OpenAudio

Speech synthesis with voice cloning and emotion control in 80+ languages, including Russian. Quality is close to paid services, but the weights are for research only.

• Voice cloning
• Emotional voiceover
• Multilingual voiceover

Sizes

0.5B – about 4.5B

Hardware

from: Laptop

Sarvam

Indian models focused on 22 languages of India. Sarvam 30B and 105B (2026) are MoE models with strong reasoning and agent skills.

• Multilingual customer support
• Reasoning and calculation tasks
• Agents with tool calling

Sizes

2B – 105B-A10B

Hardware

from: Laptop

Reka Flash и Reka Edge

Compact Reka models: Flash 3 (21B) for reasoning and Reka Edge (7B), which quickly analyzes images and video on-device.

• Photo and video analysis (Edge)
• Object detection in images
• Reasoning tasks (Flash)

Sizes

7B – 21B

Hardware

from: Laptop

InternVL

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

Molmo

Fully open vision models from Ai2 (weights and data). They can point to a spot in an image and count objects; Molmo2 understands video, MolmoWeb controls a browser.

• Counting products and objects in photos
• Pointing to where an item is in an image
• Video analysis

Sizes

1B-A7B – 72B

Hardware

from: Laptop

dots.ocr

A multilingual document parsing model: text, tables, formulas and reading order in one pass. dots.mocr also turns charts and diagrams into vector SVG.

• Recognising invoices, contracts and delivery notes
• Converting tables into an editable format
• Converting charts and diagrams into vector format

Sizes

about 3B

Hardware

from: Laptop

Chandra OCR

A strong OCR model from the authors of Marker and Surya: handwriting, forms, tables. Per the model card it supports 90+ languages, with Russian among the examples.

• Recognising invoices, contracts and delivery notes, including in Russian
• Recognising handwritten forms and questionnaires
• Recognising complex tables

Sizes

5B – 9B

Hardware

from: Laptop

Qianfan-OCR

A Baidu model that not only recognises a document but also answers questions about it. Per the model card it supports 192 languages, including Cyrillic.

• Recognising invoices, contracts and delivery notes, including in Russian
• Page layout analysis and table recognition
• Answering questions about a document

Sizes

4B

Hardware

from: Laptop

FireRedVAD

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

OmniVoice

Speech synthesis with voice cloning from a short sample in 646 languages, including Russian and languages of Russia's peoples. A voice can be described in words. Weights are for non-commercial use only.

• Voiceover in rare languages
• Voice cloning from a sample
• Research and prototypes of multilingual voiceover

Sizes

0.6B

Hardware

from: Laptop

MatAnyone

Cuts a person out of video with a precise alpha mask, including hair and edges, without a green screen. Needs a first-frame mask, for example from SAM.

• Background replacement in video without chroma key
• Cutting out a person for editing and effects
• Preparing videos for advertising and social media

Sizes

about 35M

Hardware

from: Laptop

Harrier (harrier-oss)

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

Orion-MSP / Orion-BiX

Recent open models for tabular data: they predict from a few examples given in the prompt, with no task-specific training.

• Classification and forecasting on tables with no separate training
• Quickly testing models on new datasets
• Assessing features in large tables

Sizes

size not stated on the model card

Hardware

from: Laptop

Qwen Coder

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

IQuest-Coder

A family of coding models with standard and reasoning versions, including a Loop variant that runs through its layers a second time. Sizes from 7B to 40B.

• Writing and refining code
• Solving tasks with step-by-step reasoning
• Agentic work with a repository

Sizes

7B – 40B

Hardware

from: Laptop

SERA (Ai2 Open Coding Agents)

Fully open developer agents from Ai2: weights, data and training recipe are all public. Designed so a company can cheaply fine-tune the agent on its own repository.

• An agent for fixing issues in code
• Fine-tuning the agent on an internal repository
• Automating small edits and tests

Sizes

8B – 32B

Hardware

from: Laptop

QED-Nano

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

Moshi / Hibiki

A voice assistant that listens and speaks at the same time, with no delay for recognition and synthesis. Hibiki does simultaneous speech-to-speech translation between several European languages.

• Real-time voice conversation partner
• Simultaneous speech translation
• Zero-latency voice interfaces

Sizes

2B – 7B

Hardware

from: Laptop

MiniCPM-o

A small model that sees, hears and replies by voice in real time, and can clone a voice. Voice dialogue in English and Chinese, text in 30+ languages.

• Voice assistant on your own server
• Analyzing videos and documents
• Voice answers about a camera image

Sizes

8B – 9B

Hardware

from: Laptop

GUI-Owl / Mobile-Agent

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

TabICL

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

MedGemma

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

CheXagent / CheXOne

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

Lingshu

Alibaba's medical model based on Qwen2.5-VL: understands many types of medical images and medical text, and can reason step by step. Does not replace a doctor; decisions are made by a specialist.

• Hints for doctors when reviewing images
• Draft reports and discharge summaries
• Searching medical literature

Sizes

7B – 32B

Hardware

from: Laptop

YOLO (Ultralytics)

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

Qwen3 Embedding / Reranker

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

Voyage 4 nano

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

Qwen3-TTS

Speech synthesis in 10 languages, including Russian: voice cloning from 3 seconds, ready-made voices and creating a voice from a text description.

• Voice for a bot or assistant
• Cloning a brand voice
• Choosing a voice by description

Sizes

0.6B – 1.7B

Hardware

from: Laptop

Baichuan

First general-purpose Chinese models, then a medical line from 2025. Baichuan-M3 (based on Qwen3-235B) is trained to model a doctor's clinical reasoning.

• Reference assistant for doctors
• Preliminary patient intake questions
• Analysis of medical documents

Sizes

7B – 235B-A22B

Hardware

from: Laptop

Falcon

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

Phi

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

OLMo

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

Jamba

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

EuroLLM

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

TranslateGemma

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

DeepSeek-OCR

An OCR model that compresses a page into a small number of visual tokens, so it processes large volumes quickly. Version 2 better understands reading order.

• Bulk recognition of scanned invoices and contracts
• Table recognition
• Converting PDFs to Markdown for search and RAG

Sizes

about 3B

Hardware

from: Laptop

GLM-OCR

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

LightOnOCR

A French 1B OCR model that converts a page into text in one pass and is fast on high volumes. Languages on the 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

0.9B – 1B

Hardware

from: Laptop

Foundation-Sec

Cisco models for information security based on Llama 3.1 8B: analysis of vulnerabilities, threats and incidents. Can be deployed inside your own perimeter.

• Analyzing vulnerability and threat reports
• Helping SOC analysts during incidents
• Mapping threats to MITRE ATT&CK

Sizes

8B

Hardware

from: Laptop

Smart Turn

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

Depth Anything

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

Omnilingual ASR

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

SenseVoice / Paraformer / Fun-ASR

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

CosyVoice / Fun-CosyVoice

Speech synthesis with voice cloning from a short sample and streaming output for live dialogue. Version 3 supports 9 languages, including Russian.

• Voice for a bot or assistant
• Cloning a brand voice
• Voicing videos

Sizes

300M – 0.5B

Hardware

from: Laptop

HyperCLOVA X SEED

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

Vikhr

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

CogVLM и GLM-V

Vision models from Zhipu: first CogVLM, then the GLM-V line. GLM-4.6V can call tools based on images and act as an agent operating an interface.

• Answering questions about photos and documents
• An agent that operates an interface from screenshots
• Analysing charts and reports

Sizes

9B – 106B-A12B

Hardware

from: Laptop

MAI-UI

Compact Alibaba models for working in smartphone and computer interfaces: they find elements and complete multi-step tasks. The small size allows running on an ordinary GPU.

• Automating actions in mobile apps
• Working in software without an API
• UI autotests

Sizes

2B – 8B

Hardware

from: Laptop

AprielGuard

A guard model that catches both harmful content and attacks on AI (prompt injection, jailbreaks), including when agents use tools.

• Screening chatbot requests for attacks and jailbreaks
• Filtering harmful model answers
• Monitoring the actions of AI agents that use tools

Sizes

8B

Hardware

from: Laptop

Jais

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

Perception Encoder (PE)

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

VideoSeal

A watermark for video and images that survives re-encoding and cropping. The detector errs in both directions: a missing mark does not prove a forgery, and finding one is a reason for a human to check.

• Marking video created or processed by AI
• Finding your own mark in re-uploaded clips
• Protecting ad materials from being reused as someone else's

Sizes

a mark of 96 to 1024 bits

Hardware

from: Laptop

DeepSeek-Math

DeepSeek's maths models. The first 7B version introduced the GRPO training method; the 685B V2 writes and checks its own olympiad-level proofs.

• Calculations and formula checks
• Checking mathematical workings in reports
• Working through problems step by step

Sizes

7B – 685B

Hardware

from: Laptop

Hermes

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

Silero TTS

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

Dia

A model that voices entire two-person dialogues with laughter, sighs and pauses. English only.

• Voicing dialogues and podcasts
• Ads with natural speech
• Training role-plays

Sizes

1B – 2B

Hardware

from: Laptop

Silero VAD

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

Cogito

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

IBM–ESA TerraMind

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

MetaCLIP / MetaCLIP 2

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

zerank (ZeroEntropy)

Rerankers built on Qwen3. The model card lists the target domains — finance, law, code, medicine, science; the stated language is English.

• Refining results before an AI assistant answers
• Sorting search results across contracts and reports
• Search across technical and scientific documentation

Sizes

zerank-2 — 4B (based on Qwen3-4B), plus a smaller "small" version

Hardware

from: Laptop

Grounding DINO / Rex-Omni

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

Chronos

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

DiffRhythm

Fast generation of a full song with vocals from lyrics and a style sample, up to several minutes long.

• Songs and jingles from lyrics
• Music for videos
• Demo versions of tracks

Sizes

about 1.1B

Hardware

from: Laptop

Qwen-VL

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

Nanonets-OCR

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

NVIDIA Sortformer / TitaNet

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

mxbai (Mixedbread Embed и Rerank)

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

ModernVBERT / ColModernVBERT

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

A-Vibe (Авито)

Avito's model based on Qwen3-8B, retrained for Russian: its own tokenizer makes Russian text 15–25% faster. Supports function calling.

• Product and listing descriptions in Russian
• Chatbot that calls internal services
• Request analysis and classification

Sizes

7.9B

Hardware

from: Laptop

AntiDeepfake (NII)

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

EmbeddingGemma

A small multilingual embedding model based on Gemma 3 that runs even on a phone or laptop without internet.

• On-device document search
• RAG without sending data outside
• Text classification

Sizes

300M

Hardware

from: Laptop

Vosk (русские модели)

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

Qwen Omni

Models that understand text, images, audio and video and reply by voice in real time. Qwen3-Omni speaks 10 languages, including Russian.

• Voice assistant for customers
• Analyzing calls and videos
• Voice answers about documents and images

Sizes

3B – 30B-A3B

Hardware

from: Laptop

Qwen3Guard

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

SmolDocling и Granite-Docling

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

pyannote (диаризация)

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

IBM–NASA Prithvi

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

BGE (BAAI General Embedding)

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

Prem-1B-SQL

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

RADAR

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

Kimina-Prover

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

DINOv2 / DINOv3

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

Moirai

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

Ruadapt (RuadaptQwen)

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

ClearerVoice (MossFormer)

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

LVFace

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

ESpeech-TTS

Russian speech synthesis with voice cloning based on the F5-TTS architecture, trained on Russian speech datasets collected by the authors. Stress is placed automatically. Several variants, including a "podcaster" one.

• Voicing videos and audiobooks in Russian
• Cloning a narrator's voice from a sample
• Voice for a bot or assistant in Russian

Sizes

about 340M

Hardware

from: Laptop

DeepfakeBench

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

MedSigLIP

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

II-Medical

Reasoning medical models on Qwen3, designed to run on an ordinary computer. Does not replace a doctor; decisions are made by a specialist.

• Reference answers to staff with the reasoning shown
• Draft discharge summaries for a doctor to review
• Searching medical literature

Sizes

7B – 32B

Hardware

from: Laptop

T-one

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

SmolLM

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

Seed-X

A compact ByteDance translator for 28 languages, close in quality to large closed systems. Russian is supported. Ready-made compressed versions are available.

• Translating business correspondence and documents
• Translating product cards
• Translating technical and legal texts

Sizes

7B

Hardware

from: Laptop

BiRefNet

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

Kronos

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

TEN VAD

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

DeepScaleR, DeepCoder, DeepSWE

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

ColPali / ColQwen

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

Эмоции в русской речи (модели на датасете Dusha)

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

Watermark Anything (WAM)

An image watermark that can be applied to individual regions: the model shows which part of the image is marked. It errs in both directions - a human reviews the result.

• Marking generated and edited images
• Finding a marked fragment inside a collage
• Tracking which parts of a picture were made by AI

Sizes

a mark encoder and decoder for images

Hardware

from: Laptop

CompassJudger / CompassVerifier

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

AceMath / AceReason

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

SmolVLA

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

Tower

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

GPT-SoVITS

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

Skywork-Reward

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

LatentSync

Matches lip movements in an existing video to a new voice track. Version 1.6 works at 512 pixels and produces a sharper face.

• Dubbing videos into another language with lip sync
• Editing lines in finished video without reshooting
• Talking avatars for training courses

Sizes

requires 8–18 GB of VRAM

Hardware

from: Laptop

MBZUAI TerraFM

A compact research model for satellite imagery, trained on both optical (Sentinel-2) and radar (Sentinel-1) data. Narrower in scope and community than Prithvi and TerraMind.

• Classification and segmentation of satellite imagery after fine-tuning
• A base for a land monitoring prototype

Sizes

TerraFM-B (ViT-Base)

Hardware

from: Laptop

SecGPT

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

SQL-R1

A text-to-SQL model trained with reinforcement learning: it works through the schema and the conditions step by step before producing a query.

• Database queries for questions with several conditions
• Reviewing and fixing other people SQL queries
• An analyst helper inside a BI system

Sizes

3B – 14B

Hardware

from: Laptop

JobBERT (TechWolf)

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

DeepSeek-R1

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

Seed-Coder

A compact 8B coding model from ByteDance in base, instruct and reasoning versions. Its training data was selected by the model itself, with almost no hand-written rules.

• Code autocompletion and generation
• Solving algorithmic problems
• A base for fine-tuning on your own stack

Sizes

8B

Hardware

from: Laptop

RuModernBERT и USER (deepvk)

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

Arctic-Text2SQL-R1

A Snowflake model for turning questions into SQL, trained with reinforcement learning by checking query results. The open 7B version is based on Qwen2.5-Coder.

• Plain-language questions to a data warehouse
• Generating SQL for reports and dashboards
• Checking and fixing analysts' queries

Sizes

7B

Hardware

from: Laptop

Kodify-Nano (МТС AI)

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

ColBERT (поиск с поздним взаимодействием)

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

Sundial

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

Llama

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

DeepSeek-Prover

DeepSeek models for formal proofs in Lean 4: the proof is checked by a program, not a person. A narrow tool for mathematicians and engineers.

• Formal verification of mathematical workings
• Verifying algorithm correctness
• Training and olympiad preparation

Sizes

7B – 671B

Hardware

from: Laptop

Saiga

The best-known Russian community fine-tune: open models (Llama, Mistral, Gemma, YandexGPT) trained to act as a Russian-speaking assistant. A convenient starting point for a Russian chatbot on your own server.

• Russian-language chat assistant
• Answers based on the company knowledge base
• Drafts of emails, descriptions and posts in Russian

Sizes

7B – 70B

Hardware

from: Laptop

Llama Guard

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

Prompt Guard

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

CatVTON / CatV2TON

A lightweight try-on model that runs on a regular GPU. There is a mask-free version and CatV2TON, which also tries clothes on in video.

• Trying a garment on a customer's photo
• Draft product cards on a model
• Try-on in a short video

Sizes

899M

Hardware

from: Laptop

SmolVLM

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

Seed-VC

Voice conversion without training: transfers timbre from a 1–30 second sample, can sing and work in real time; V2 also changes accent. Use only with the voice owner's consent.

• Re-voicing a video with a different voice
• Voice anonymization in recordings
• Real-time voice for streams

Sizes

about 70M – 200M

Hardware

from: Laptop

UI-TARS

A model that looks at a screenshot and controls the mouse and keyboard itself: clicks, fills in fields, navigates menus. The first generation and 1.5-7B are open; UI-TARS-2 weights were not released.

• Working in legacy software without an API
• Filling in forms and moving data between systems
• UI autotests from plain-language scenarios

Sizes

2B – 72B

Hardware

from: Laptop

XiYanSQL-QwenCoder

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

NSFW-классификаторы (Falconsai, Freepik)

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

WhiteRabbitNeo / DeepHat

One of the best-known open families for security and DevSecOps work: reviewing code for weaknesses, test scenarios, explaining attacks.

• Finding weak spots in code and configurations
• Reviewing incidents and explaining attack techniques
• Drafting scripts and procedures for the security team

Sizes

7B – 70B

Hardware

from: Laptop

Whisper

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

SANA

NVIDIA's fast image model: 4K images in seconds, runs even on a laptop GPU. The Sprint version generates in 1–2 steps.

• Bulk image generation
• High-resolution visuals
• Real-time generation inside apps

Sizes

0.6B – 4.8B

Hardware

from: Laptop

MuseTalk

Real-time lip sync: matches the mouth in a video to new audio. Suits video translation and live avatars.

• Dubbing video into another language
• Live avatar in a video chat
• Editing speech in a finished video

Sizes

under 1B

Hardware

from: Laptop

s1

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

Light-R1

Reasoning models from Qihoo 360: a standard Qwen2.5 was fine-tuned for long reasoning using an open recipe; data and code are published.

• Calculations and formula checks
• Working through problems step by step
• A base for your own reasoning fine-tuning

Sizes

7B – 32B

Hardware

from: Laptop

Nomic Embed

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

Piper

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

F5-TTS

A voice cloning model that needs only a few seconds of a sample, in English and Chinese. The community has released many fine-tuned versions for other languages, including Russian.

• Voice cloning
• Voicing audiobooks and videos
• Research and prototypes

Sizes

about 340M

Hardware

from: Laptop

Orpheus TTS

Language-model-based speech synthesis with lively intonation and emotional cues. Responds quickly, suitable for voice assistants. Mainly English.

• Real-time voice for an assistant
• Emotional voiceover
• Voice cloning

Sizes

3B

Hardware

from: Laptop

Sesame CSM

A conversational speech model that takes the context of the conversation into account and sounds like a real person. English only.

• Voice for a conversational assistant
• Voicing dialogues
• Voice product prototypes

Sizes

1B

Hardware

from: Laptop

ShieldGemma

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

OmniSQL

Models for turning questions into SQL, trained on millions of synthetic query examples across different databases. Three sizes for different hardware.

• Database questions without knowing SQL
• Generating queries for reports
• A base for fine-tuning on your own database schema

Sizes

7B – 32B

Hardware

from: Laptop

xLAM

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

Fin-R1

A reasoning model for financial tasks based on Qwen2.5-7B: calculations, report analysis, regulatory questions. Trained on Chinese and English data.

• Financial calculations with step-by-step explanations
• Answering questions about financial statements
• Analyzing tables of financial data

Sizes

7B

Hardware

from: Laptop

Desklib AI Text Detector

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

Sky-T1

A Berkeley reasoning model trained for under 450 dollars. It showed that o1-preview-level reasoning can be reproduced with modest resources.

• Calculations and formula checks
• Working through problems step by step
• A base for your own reasoning fine-tuning

Sizes

7B – 32B

Hardware

from: Laptop

SigLIP (наследник CLIP)

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

Tulu

Ai2 fine-tunes of Llama with a fully open recipe: data, code and all intermediate stages. Tulu 3 405B is one of the largest openly fine-tuned models; OLMo chat versions use the same recipe.

• Employee assistant on your own server
• Math and precise instruction following
• Reference recipe for your own fine-tuning

Sizes

7B – 405B

Hardware

from: Laptop

Kokoro

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

OmniParser

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

Llama-Primus

Trend Micro cybersecurity models based on Llama 3.1 8B, fine-tuned on a corpus of security texts. A reasoning version is available.

• Answering questions about threats and vulnerabilities
• Analyzing cyberattack reports
• A base for fine-tuning for SOC tasks

Sizes

8B

Hardware

from: Laptop

ALLaM

A Saudi model for Arabic and English, trained from scratch. One 7B version is openly available.

• An Arabic-language assistant
• Answering questions about documents
• Writing and editing texts in Arabic

Sizes

7B

Hardware

from: Laptop

Bioptimus H-optimus

Pathology foundation models from France's Bioptimus with 1.1B parameters, plus the compact H0-mini. The first version is open under Apache 2.0. Does not replace a doctor; decisions are made by a specialist.

• Histology slide patch features for research models
• A prototype for sorting slides by tissue type
• Research projects linking morphology and molecular data

Sizes

86M (H0-mini) – 1,1B

Hardware

from: Laptop

CareerBERT

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

Qwen2.5-Math

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

GTE

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

ModernBERT

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

BEN2

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

Janus

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

ViTPose

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

VideoLLaMA

Models that watch a video and answer questions about it: what happens, when, who does what. VideoLLaMA 3 at 2B and 7B is among the strongest in its size class.

• Video description and short summary
• Finding a moment in a recording by question
• Tagging a video archive

Sizes

2B – 72B

Hardware

from: Laptop

MahmoodLab UNI / UNI 2

A foundation model for histology slides: turns patches of digital slides into features for tissue classification. Does not replace a doctor; decisions are made by a specialist.

• Research classifiers of tissue types from digital slides
• Finding similar cases in a slide archive
• Preparing features for research prognosis models

Sizes

about 300M (UNI) – about 680M (UNI2-h)

Hardware

from: Laptop

Sentence Transformers (all-MiniLM, paraphrase-multilingual)

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

ReaderLM (Jina)

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

LlamaIndex vdr

A small model for searching document pages as images, from the team behind a popular RAG framework. The card lists English, Italian, French, German and Spanish.

• Search across scans and PDFs without OCR
• Search across invoices, acts and contracts
• Picking pages for an AI assistant answer

Sizes

2B (based on Qwen2-VL)

Hardware

from: 1 GPU

Atla Selene

An 8B judge model: it scores another model answer against your criteria and writes a rationale. The judge itself makes mistakes and does not replace manual review on important tasks.

• Scoring chatbot answers against your own criteria
• Comparing two versions of a prompt or model
• Filtering out weak answers before they reach a person

Sizes

8B

Hardware

from: 1 GPU

MMAudio

Adds sound to silent video: generates noises and sound effects in sync with the on-screen action, from the video and a text prompt. One of the first strong open Foley models.

• Sound effects for silent video
• Sound for clips from AI generators
• Draft sound design for editing

Sizes

size not stated on the model card

Hardware

from: Laptop

MuQ / MuQ-MuLan

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

MahmoodLab CONCH / TITAN

Image-plus-text models for pathology: search slides by an English description, classify without fine-tuning; TITAN describes a whole slide. Does not replace a doctor; decisions are made by a specialist.

• Text-query search across a slide archive for research
• Draft slide descriptions for research projects
• Tissue classification without labels at the start of a study

Sizes

about 160M – 300M

Hardware

from: Laptop

Snowflake Arctic Embed

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

AudioSeal

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

ConTeXT-Skill-Extraction

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

GME (General Multimodal Embedding)

One vector for text, for an image and for a text-image pair: a single model can find a product by photo, a document page by question and an image by description. The card lists English and Chinese.

• Finding a product by photo
• Search across a catalogue of images and cards
• Search across document pages as images

Sizes

2B and 7B

Hardware

from: 1 GPU

GLIDER (Patronus)

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

Parler-TTS

Speech synthesis where the voice is set by a text description ("a calm female voice, clean recording"). English and 8 European languages, no Russian.

• Choosing a voice by description
• Voicing videos
• Voice service prototypes

Sizes

880M – 2.2B

Hardware

from: Laptop

MusicGen (AudioCraft)

Generates instrumental music from a text description or a sample melody. One of the first open models of its kind.

• Draft music sketches
• Music for video prototypes
• Research

Sizes

300M – 3.3B

Hardware

from: Laptop

PaliGemma

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

GOT-OCR 2.0

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

OpenCoder

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

Cotype Nano (МТС AI)

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

kazRush (deepvk)

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

FinMA (PIXIU)

One of the first open model families for financial text: reading statements, news and questions about numbers. Not investment advice: decisions are made by a specialist.

• Reading financial statements and press releases
• Answering questions about numeric data in documents
• Classifying financial texts

Sizes

0.5B – 30B

Hardware

from: Laptop

Stable Diffusion

The model that started open image generation. A huge ecosystem of fine-tunes, styles and plugins; runs even on a home PC. The popular SDXL-Lightning and Hyper-SD accelerators were made by ByteDance.

• Illustrations and banners for advertising
• Backgrounds and scenes for product cards
• Fine-tuning to a brand style

Sizes

0.9B – 8B

Hardware

from: Laptop

RIFE (Practical-RIFE)

Generates intermediate frames: turns 24–30 fps into 60 fps and more and makes smooth slow motion. Versions 4.24+ smooth out video from generative models well.

• Increasing video frame rate
• Smooth slow-motion video
• Smoothing clips from AI generators

Sizes

lightweight model (size not stated on the model card)

Hardware

from: Laptop

Phishing Email Detection DistilBERT

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

MonoQwen2-VL (LightOn)

A reranker for document pages as images: after a visual search it reorders the found pages by how well they answer the question. The card does not state the languages.

• Refining search results over scans and PDFs
• Selecting pages before an AI assistant answers
• Sorting retrieved slides and reports

Sizes

2B (based on Qwen2-VL)

Hardware

from: 1 GPU

MOMENT

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

Granite Time Series (TinyTimeMixers, PatchTST)

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

DeepSeek-Coder

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

Piiranha

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

Yi-Coder

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