README.md

---
base_model: unsloth/Llama-3.3-70B-Instruct
language:
- en
library_name: transformers
license: llama3.3
tags:
- llama-3
- llama
- meta
- facebook
- unsloth
- transformers
- pytorch
- mlx
- mlx-my-repo
---

# cnfusion/Llama-3.3-70B-Instruct-Q2-mlx

The Model [cnfusion/Llama-3.3-70B-Instruct-Q2-mlx](https://huggingface.co/cnfusion/Llama-3.3-70B-Instruct-Q2-mlx) was converted to MLX format from [unsloth/Llama-3.3-70B-Instruct](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct) using mlx-lm version **0.19.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("cnfusion/Llama-3.3-70B-Instruct-Q2-mlx")

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)
```