---
license: apache-2.0
library_name: mlx
tags:
- language
- granite-4.0
- mlx
base_model:
- ethicalabs/granite-4.0-h-1b-MLX
- ethicalabs/kurtis-e1-granite-4.0-h-1b-adapter-MLX
pipeline_tag: text-generation
datasets:
- ethicalabs/Kurtis-E1-SFT
- ethicalabs/kurtis-v2-sft-mix-tiny
base_model_relation: merge
---

# ethicalabs/kurtis-e1-granite-4.0-h-1b-MLX

This model [ethicalabs/kurtis-e1-granite-4.0-h-1b-MLX](https://huggingface.co/ethicalabs/kurtis-e1-granite-4.0-h-1b-MLX) was
converted to MLX format from [ethicalabs/granite-4.0-h-1b-MLX](https://huggingface.co/ethicalabs/granite-4.0-h-1b-MLX)
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("ethicalabs/kurtis-e1-granite-4.0-h-1b-MLX")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```