---
language:
- zh
- en
license: apache-2.0
tags:
- mlx
---

# xiaotianxt/llama-3-chinese-8b-instruct-v3-4bit-mlx

The Model [xiaotianxt/llama-3-chinese-8b-instruct-v3-4bit-mlx](https://huggingface.co/xiaotianxt/llama-3-chinese-8b-instruct-v3-4bit-mlx) was converted to MLX format from [hfl/llama-3-chinese-8b-instruct-v3](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-v3) using mlx-lm version **0.14.0**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("xiaotianxt/llama-3-chinese-8b-instruct-v3-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```