TextTranslationSearch and RAGDocuments and OCR

Лаборатория ИИ СВФУ: якутский язык

The most complete set of models for the Sakha (Yakut) language in one place: language models of several sizes, translation to and from Russian, embeddings and text recognition from images. Quality varies, so test it on your own data.

Developer
AI Laboratory of the North-Eastern Federal University, Russia
First release
Jun 2025
Latest release
Sep 2026
Sizes
1.1B – 27B
License
Commercial use with conditionsvaries by model: Apache 2.0, MIT, CC-BY 4.0, Gemma Terms; some models state no license
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Education, Public sector, Media and production, Documents and accounting

What it does

  • Answering and writing in the Sakha language
  • Translating documents and materials
  • Semantic search over Sakha texts
  • Reading Sakha text from scans and photos

Where it is used

Education and researchGovernment and municipal bodiesMedia and publishing

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. Эмбеддинги sakha-embed-mmbert и распознавание текста sakha-ocr
  2. TranslateGemma 12B для якутского
  3. Qwen3.5 27B для якутского
  4. Qwen3 4B и Llama 3.2 для якутского
  5. Aina 14B Instruct
  6. mT5 для перевода русский — якутский
  7. TinyLlama Sakha Instruct

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Лаборатория ИИ СВФУ: якутский язык be used in a commercial project?

With conditions. License: varies by model: Apache 2.0, MIT, CC-BY 4.0, Gemma Terms; some models state no license. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Лаборатория ИИ СВФУ: якутский язык need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Лаборатория ИИ СВФУ: якутский язык support Russian?

Yes, Russian is listed on the model card.

Where can I download Лаборатория ИИ СВФУ: якутский язык and what does it cost?

The Лаборатория ИИ СВФУ: якутский язык weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Source: huggingface.co/lab-ii/Qwen3.5-27B-sah. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.