---
tags:
- mlx
datasets:
- Yukang/LongAlpaca-16k-length
---

# mattshumer/Llama-3-8B-16K-4bit
This model was converted to MLX format from [`mattshumer/Llama-3-8B-16K`](https://huggingface.co/mattshumer/Llama-3-8B-16K) using mlx-lm version **0.10.0**.
Refer to the [original model card](https://huggingface.co/mattshumer/Llama-3-8B-16K) for more details on the model.
## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mattshumer/Llama-3-8B-16K-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```