---
library_name: transformers
tags:
- mlx
---

# cmcmaster/rheum-gemma-2-2b-it-mlx-4bit

The Model [cmcmaster/rheum-gemma-2-2b-it-mlx-4bit](https://huggingface.co/cmcmaster/rheum-gemma-2-2b-it-mlx-4bit) was converted to MLX format from [cmcmaster/rheum-gemma-2-2b-it](https://huggingface.co/cmcmaster/rheum-gemma-2-2b-it) using mlx-lm version **0.18.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("cmcmaster/rheum-gemma-2-2b-it-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```