TextSpeech to textVoice assistants

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.

Developer
Vikhr Models, Russia
First release
Jan 2024
Latest release
Dec 2025
Sizes
0.5B – 24B
License
Commercial use allowedMain versions: Apache 2.0; some fine-tunes inherit the base model license (Llama, YandexGPT)
Russian
Supported
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Education, Marketing and content
Deploy on your server Hugging Face GitHub

What it does

  • Russian-language assistant on your own PC or server
  • Knowledge-base answers (RAG)
  • Texts and emails in Russian

Where it is used

Small businessCustomer supportEducation

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. Borealis-5B-it
  2. Vistral-24B / Borealis (речь в текст)
  3. QVikhr-3 (1.7B–8B)
  4. QVikhr-2.5-1.5B
  5. Vikhr-Nemo-12B / Llama3.1-8B
  6. Vikhr-7B

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. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Vikhr be used in a commercial project?

Yes. License: Main versions: Apache 2.0; some fine-tunes inherit the base model license (Llama, YandexGPT). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Vikhr 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 Vikhr support Russian?

Yes, Russian is listed on the model card.

Where can I download Vikhr and what does it cost?

The Vikhr 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

TextT-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.

DetailsTextGigaChatSber · 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.

Details

Source: huggingface.co/Vikhrmodels/Vistral-24B-Instruct. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.