---
license: llama3
tags:
- mlx
---

# mlx-community/Llama-3-8b-Cosmopedia-japanese-4bit

The Model [mlx-community/Llama-3-8b-Cosmopedia-japanese-4bit](https://huggingface.co/mlx-community/Llama-3-8b-Cosmopedia-japanese-4bit) was converted to MLX format from [aixsatoshi/Llama-3-8b-Cosmopedia-japanese](https://huggingface.co/aixsatoshi/Llama-3-8b-Cosmopedia-japanese) using mlx-lm version **0.14.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Llama-3-8b-Cosmopedia-japanese-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```