baichuan
13B parameters
Restricted
Reviewed May 2026Baichuan 4 13B
Baichuan AI's 13B. Chinese-language ecosystem alternative to Qwen / GLM. Restricted commercial license.
License: Baichuan License·Released Oct 30, 2024·Context: 131,072 tokens
Overview
Baichuan AI's 13B. Chinese-language ecosystem alternative to Qwen / GLM. Restricted commercial license.
Strengths
- Chinese-language depth
Weaknesses
- Restricted license
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 7.8 GB | 10 GB |
Get the model
HuggingFace
Original weights
huggingface.co/baichuan-inc/Baichuan4-13B
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of Baichuan 4 13B.
Frequently asked
What's the minimum VRAM to run Baichuan 4 13B?
10GB of VRAM is enough to run Baichuan 4 13B at the Q4_K_M quantization (file size 7.8 GB). Higher-quality quantizations need more.
Can I use Baichuan 4 13B commercially?
Baichuan 4 13B is released under the Baichuan License, which has restrictions for commercial use. Review the license terms before using it in a product.
What's the context length of Baichuan 4 13B?
Baichuan 4 13B supports a context window of 131,072 tokens (about 131K).
Source: huggingface.co/baichuan-inc/Baichuan4-13B
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Compare hardware
Buyer guides
Before you buy
Verify Baichuan 4 13B runs on your specific hardware before committing money.