---
base_model: mlx-community/Qwen3.5-0.8B-MLX-4bit
library_name: mlx
tags:
- mlx
- qwen3.5
- vision-language-model
- quantized
- 4bit
license: apache-2.0
pipeline_tag: text-generation
---

# YoozLabs/Yooz-Quality-v2.1-Qwen3.5-0.8B

This model [YoozLabs/Yooz-Quality-v2.1-Qwen3.5-0.8B](https://huggingface.co/YoozLabs/Yooz-Quality-v2.1-Qwen3.5-0.8B) was
converted to MLX format from [mlx-community/Qwen3.5-0.8B-MLX-4bit](https://huggingface.co/mlx-community/Qwen3.5-0.8B-MLX-4bit)
using mlx-lm version **0.31.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("YoozLabs/Yooz-Quality-v2.1-Qwen3.5-0.8B")

prompt = "hello"

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

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