README.md

---
language:
- en
license: other
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- moe
- code
- mlx
base_model: meta-llama/Meta-Llama-3-8B-Instruct
pipeline_tag: text-generation
license_name: llama3
license_link: LICENSE
---

# mlx-community/Llama-3-Aplite-Instruct-4x8B-MoE-4bit
This model was converted to MLX format from [`raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE`]() using mlx-lm version **0.12.0**.
Refer to the [original model card](https://huggingface.co/raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE) 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/Llama-3-Aplite-Instruct-4x8B-MoE-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```