---
tags:
- general-purpose
- roleplay
- creative-writing
- storywriting
- granite-4.1
- finetune
- SFT
- text-generation-inference
- mlx
- mlx-my-repo
language:
- en
- pt
base_model: aimeri/spoomplesmaxx-v2-30B
pipeline_tag: text-generation
library_name: transformers
datasets:
- aimeri/spoomplesmaxx-sft-full-v1
---

# aimeri/spoomplesmaxx-v2-30B-mlx-4Bit

The Model [aimeri/spoomplesmaxx-v2-30B-mlx-4Bit](https://huggingface.co/aimeri/spoomplesmaxx-v2-30B-mlx-4Bit) was converted to MLX format from [aimeri/spoomplesmaxx-v2-30B](https://huggingface.co/aimeri/spoomplesmaxx-v2-30B) using mlx-lm version **0.31.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("aimeri/spoomplesmaxx-v2-30B-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)
```