README.md

---
tags:
- mlx
- mlx
- mlx-my-repo
base_model: mlx-community/IBM-granite-3.2-2b-instruct-4bit
---

# introvoyz041/IBM-granite-3.2-2b-instruct-4bit-mlx-4Bit

The Model [introvoyz041/IBM-granite-3.2-2b-instruct-4bit-mlx-4Bit](https://huggingface.co/introvoyz041/IBM-granite-3.2-2b-instruct-4bit-mlx-4Bit) was converted to MLX format from [mlx-community/IBM-granite-3.2-2b-instruct-4bit](https://huggingface.co/mlx-community/IBM-granite-3.2-2b-instruct-4bit) 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("introvoyz041/IBM-granite-3.2-2b-instruct-4bit-mlx-4Bit")

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)
```