README.md

---
language:
- code
license: other
tags:
- code
- mlx
inference: false
license_name: mnpl
license_link: https://mistral.ai/licences/MNPL-0.1.md
---

# mlx-community/Codestral-22B-v0.1-4bit

The Model [mlx-community/Codestral-22B-v0.1-4bit](https://huggingface.co/mlx-community/Codestral-22B-v0.1-4bit) was converted to MLX format from [bullerwins/Codestral-22B-v0.1-hf](https://huggingface.co/bullerwins/Codestral-22B-v0.1-hf) 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("mlx-community/Codestral-22B-v0.1-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```