---
license: apache-2.0
tags:
- merge
- mergekit
- creative-writing
- storytelling
- mlx
- mlx-my-repo
base_model: Ateron/Gemma-4-Novelist-31B
model_creator: Blazed-Forge
pipeline_tag: text-generation
quantized_by: f16
language:
- en
---

# McG-221/Gemma-4-Novelist-31B-mlx-8Bit

The Model [McG-221/Gemma-4-Novelist-31B-mlx-8Bit](https://huggingface.co/McG-221/Gemma-4-Novelist-31B-mlx-8Bit) was converted to MLX format from [Ateron/Gemma-4-Novelist-31B](https://huggingface.co/Ateron/Gemma-4-Novelist-31B) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("McG-221/Gemma-4-Novelist-31B-mlx-8Bit")

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)
```