Text

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.

Developer
T-Bank, Russia
First release
Dec 2024
Latest release
Jul 2026
Sizes
7B – 36B-A3B
License
Commercial use allowedApache 2.0 (versions 2.0, 2.1 and T-Search; based on Qwen)
Russian
Supported
Running
On your own serverNeeds a GPU
Industries
Finance, Customer support, Legal, HR
Deploy on your server Hugging Face

What it does

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

Where it is used

Banking and fintechCustomer supportLegal and HRRetail

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. T-Search 36B-A3B
  2. T-Lite / T-Pro 2.1
  3. T-Pro 2.0
  4. T-Lite / T-Pro 1.0

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 T-Pro / T-Lite be used in a commercial project?

Yes. License: Apache 2.0 (versions 2.0, 2.1 and T-Search; based on Qwen). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does T-Pro / T-Lite need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does T-Pro / T-Lite support Russian?

Yes, Russian is listed on the model card.

Where can I download T-Pro / T-Lite and what does it cost?

The T-Pro / T-Lite 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.

Comparisons

Similar models

TextGigaChatSber · RussiaCommercial use allowed

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.

DetailsTextYandexGPT / AliceAIYandex · RussiaCommercial use with conditions

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.

DetailsTextQwenAlibaba · 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.

Details

Source: huggingface.co/t-tech/T-pro-it-2.1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.