---
license: cc-by-nc-4.0
base_model: FrontisAI/Frontis-MA1-30B
base_model_relation: finetune
library_name: transformers
pipeline_tag: text-generation
tags:
- openmle
- frontis-ma1
- machine-learning-engineering
- autoresearch
- agent
- coding
- qwen3
- moe
- post-training
- mlx
- mlx-my-repo
---

# Kagandi/Frontis-MA1-30B-mlx-4Bit

The Model [Kagandi/Frontis-MA1-30B-mlx-4Bit](https://huggingface.co/Kagandi/Frontis-MA1-30B-mlx-4Bit) was converted to MLX format from [FrontisAI/Frontis-MA1-30B](https://huggingface.co/FrontisAI/Frontis-MA1-30B) 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("Kagandi/Frontis-MA1-30B-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)
```