---
library_name: mlx
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3Guard-Gen-4B/blob/main/LICENSE
pipeline_tag: text-generation
base_model: Qwen/Qwen3Guard-Gen-4B
tags:
- mlx
---

# Otilde/Qwen3Guard-Gen-4B-MLX-Q8

This model [Otilde/Qwen3Guard-Gen-4B-MLX-Q8](https://huggingface.co/Otilde/Qwen3Guard-Gen-4B-MLX-Q8) was
converted to MLX format from [Qwen/Qwen3Guard-Gen-4B](https://huggingface.co/Qwen/Qwen3Guard-Gen-4B)
using mlx-lm version **0.28.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Otilde/Qwen3Guard-Gen-4B-MLX-Q8")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```