---
language:
- en
license: apache-2.0
tags:
- mlx
datasets:
- teknium/OpenHermes-2.5
base_model: mistral-community/Mixtral-8x22B-v0.1
---

# mlx-community/mixtral-8x22b-instruct-oh-4bit
This model was converted to MLX format from [`fireworks-ai/mixtral-8x22b-instruct-oh`]() using mlx-lm version **0.9.0**.

Model added by [Prince Canuma](https://twitter.com/Prince_Canuma).

Refer to the [original model card](https://huggingface.co/fireworks-ai/mixtral-8x22b-instruct-oh) for more details on the model.
## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/mixtral-8x22b-instruct-oh-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```