TextMath and reasoning

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.

Developer
Lomonosov Moscow State University Research Computing Center, LAIR lab (RefalMachine), Russia
First release
Feb 2024
Latest release
Aug 2025
Sizes
1.5B – 32B
License
Commercial use allowedApache 2.0 for the main versions based on Qwen2.5 and Qwen3; the Qwen2.5-3B version inherits Qwen's research license
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Documents and accounting, Education
Deploy on your server Hugging Face GitHub

What it does

  • Russian-language assistant on your own server
  • Answers based on company documents (RAG) in Russian
  • Analysis and summaries of long Russian texts
  • Step-by-step reasoning in versions with a thinking mode

Where it is used

Customer supportLegal and document managementAnalyticsIT department

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
no versions

Versions

  1. RuadaptQwen3 4B Instruct / 8B Hybrid
  2. RuadaptQwen3 32B Instruct
  3. Ruadapt QwQ 32B (рассуждения)
  4. RuadaptQwen2.5 14B Instruct
  5. RuadaptQwen2.5 32B Instruct
  6. RuadaptQwen2.5 3B / 7B Instruct
  7. Ruadapt Llama 3 8B Instruct
  8. Ruadapt Solar 10.7B (исследовательская)

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 Ruadapt (RuadaptQwen) be used in a commercial project?

Yes. License: Apache 2.0 for the main versions based on Qwen2.5 and Qwen3; the Qwen2.5-3B version inherits Qwen's research license. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Ruadapt (RuadaptQwen) 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 Ruadapt (RuadaptQwen) support Russian?

Yes, Russian is listed on the model card.

Where can I download Ruadapt (RuadaptQwen) and what does it cost?

The Ruadapt (RuadaptQwen) 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

TextQwenAlibaba · ChinaCommercial use with conditions

A family of language models with strong Russian language support, from small versions for a laptop to a flagship on par with commercial APIs.

DetailsTextSaigaIlya Gusev (IlyaGusev) · RussiaCommercial use with conditions

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.

DetailsTextT-Pro / T-LiteT-Bank · RussiaCommercial use allowed

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.

Details

Source: huggingface.co/RefalMachine/RuadaptQwen3-4B-Instruct. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.