Text

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.

Developer
Baichuan Intelligence, China
First release
Jun 2023
Latest release
Jan 2026
Sizes
7B – 235B-A22B
License
Commercial use with conditionsBaichuan-M2 and M3: Apache 2.0; Baichuan 1/2: own license (commercial use on application)
Russian
Not supported
Ready-made builds
GGUF, GPTQ
Running
On your own serverNeeds a GPU
Industries
Healthcare
Deploy on your server Hugging Face GitHub

What it does

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

Where it is used

ClinicsTelemedicinePharmaHealth insurance

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. Baichuan-M3-235B
  2. Baichuan-M2-32B
  3. Baichuan-M1-14B
  4. Baichuan 2
  5. Baichuan-13B
  6. Baichuan-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 Baichuan be used in a commercial project?

With conditions. License: Baichuan-M2 and M3: Apache 2.0; Baichuan 1/2: own license (commercial use on application). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Baichuan 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 Baichuan support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Baichuan and what does it cost?

The Baichuan 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.

DetailsTextYi01.AI · ChinaCommercial use allowed

Bilingual (English and Chinese) 01.AI models of 6–34B, with versions supporting up to 200K tokens of context. No new open releases since 2024.

DetailsTextInternLM / Intern-SShanghai AI Laboratory · ChinaCommercial use allowed

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.

Details

Source: huggingface.co/baichuan-inc/Baichuan-M3-235B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.