Baichuan 2-7B
Baichuan 2-7B is an open-weights language model from Baichuan, released September 20, 2023. It has 7B parameters (dense). On the Epoch Capabilities Index it scores 83.8, rank 235 of 256 rated models.
Check it against your own PC →
Lab
Baichuan
Released
September 20, 2023
Weights
Open restricted use
Parameters
7B dense
Context
–
Price / M tokens
–
Epoch ECI
83.8 #235
Can you run Baichuan 2-7B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, split GPU / CPU, roughly 8 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 5.2 GB | 3.3 GB | ~8 |
| 8 GB VRAM | Runs on GPU | Q4_K_M (very good) | 7.0 GB | – | ~37 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 8.5 GB | – | ~36 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 8.5 GB | – | ~50 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 8.5 GB | – | ~89 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 8.5 GB | – | ~160 |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MMLU | 38.9% |
Links
Models with a similar score
MPT-30B · LLaMA-13B · internlm-7b · INTELLECT-1 · Llama 2-7B