README.md

---
pipeline_tag: text-generation
inference: false
license: apache-2.0
library_name: transformers
tags:
- language
- granite-3.2
- mlx
- mlx-my-repo
base_model: ibm-granite/granite-3.2-2b-instruct
---

# zshannon/granite-3.2-2b-instruct-Q4-mlx

The Model [zshannon/granite-3.2-2b-instruct-Q4-mlx](https://huggingface.co/zshannon/granite-3.2-2b-instruct-Q4-mlx) was converted to MLX format from [ibm-granite/granite-3.2-2b-instruct](https://huggingface.co/ibm-granite/granite-3.2-2b-instruct) using mlx-lm version **0.21.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("zshannon/granite-3.2-2b-instruct-Q4-mlx")

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)
```