# Test Time Scaling with MLX LM and R1-based LLMs

Install MLX LM:

```
pip install mlx-lm
```

And run:

```
python reason.py
```

The default model is `mlx-community/DeepSeek-R1-Distill-Qwen-7B-4bit`. You
can specify the model with `--model`.

To see all the options:

```
python reason.py --help
```