README.md

---
base_model: YOYO-AI/QwQ-coder-32B
library_name: transformers
tags:
- mergekit
- merge
- mlx
- mlx-my-repo
---

# cnfusion/QwQ-coder-32B-mlx-3Bit

The Model [cnfusion/QwQ-coder-32B-mlx-3Bit](https://huggingface.co/cnfusion/QwQ-coder-32B-mlx-3Bit) was converted to MLX format from [YOYO-AI/QwQ-coder-32B](https://huggingface.co/YOYO-AI/QwQ-coder-32B) 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("cnfusion/QwQ-coder-32B-mlx-3Bit")

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)
```