---
tags:
- unsloth
- mlx
- mlx-my-repo
base_model: unsloth/Qwen3-Next-80B-A3B-Thinking
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking/blob/main/LICENSE
pipeline_tag: text-generation
---

# McG-221/Qwen3-Next-80B-A3B-Thinking-mlx-5Bit

The Model [McG-221/Qwen3-Next-80B-A3B-Thinking-mlx-5Bit](https://huggingface.co/McG-221/Qwen3-Next-80B-A3B-Thinking-mlx-5Bit) was converted to MLX format from [unsloth/Qwen3-Next-80B-A3B-Thinking](https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Thinking) 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("McG-221/Qwen3-Next-80B-A3B-Thinking-mlx-5Bit")

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)
```