---
license: apache-2.0
tags:
- mlx
---

# cobrakenji/granite-7b-base-4bit

The Model [cobrakenji/granite-7b-base-4bit](https://huggingface.co/cobrakenji/granite-7b-base-4bit) was converted to MLX format from [ibm-granite/granite-7b-base](https://huggingface.co/ibm-granite/granite-7b-base) using mlx-lm version **0.13.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("cobrakenji/granite-7b-base-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```