---
library_name: transformers
tags:
- mlx
- mlx-my-repo
base_model: Fan1018/QWQ-RPMax-Planet-32B-ablated
---

# Wwayu/QWQ-RPMax-Planet-32B-ablated-mlx-4Bit

The Model [Wwayu/QWQ-RPMax-Planet-32B-ablated-mlx-4Bit](https://huggingface.co/Wwayu/QWQ-RPMax-Planet-32B-ablated-mlx-4Bit) was converted to MLX format from [Fan1018/QWQ-RPMax-Planet-32B-ablated](https://huggingface.co/Fan1018/QWQ-RPMax-Planet-32B-ablated) using mlx-lm version **0.26.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Wwayu/QWQ-RPMax-Planet-32B-ablated-mlx-4Bit")

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)
```