---
license: apache-2.0
tags:
- mlx
- mlx
- mlx-my-repo
base_model: mlx-community/Mixtral-8x22B-Instruct-v0.1-8bit
---

# Fmuaddib/Mixtral-8x22B-Instruct-v0.1-8bit-mlx-8Bit

The Model [Fmuaddib/Mixtral-8x22B-Instruct-v0.1-8bit-mlx-8Bit](https://huggingface.co/Fmuaddib/Mixtral-8x22B-Instruct-v0.1-8bit-mlx-8Bit) was converted to MLX format from [mlx-community/Mixtral-8x22B-Instruct-v0.1-8bit](https://huggingface.co/mlx-community/Mixtral-8x22B-Instruct-v0.1-8bit) using mlx-lm version **0.22.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Fmuaddib/Mixtral-8x22B-Instruct-v0.1-8bit-mlx-8Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```