---
license: apache-2.0
thumbnail: /static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F6625f4a8a8d1362ebcc3851a%2FhIZ2ZcaDyfYLT9Yd4pfOs.jpeg
language:
- en
base_model: ArliAI/QwQ-32B-ArliAI-RpR-v4
library_name: transformers
pipeline_tag: text-generation
tags:
- mlx
---

# Wwayu/QwQ-32B-ArliAI-RpR-v4-mlx-6Bit

The Model [Wwayu/QwQ-32B-ArliAI-RpR-v4-mlx-6Bit](https://huggingface.co/Wwayu/QwQ-32B-ArliAI-RpR-v4-mlx-6Bit) was converted to MLX format from [ArliAI/QwQ-32B-ArliAI-RpR-v4](https://huggingface.co/ArliAI/QwQ-32B-ArliAI-RpR-v4) 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-32B-ArliAI-RpR-v4-mlx-6Bit")

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)
```