[mft_]

There is a Gemma 4 model with 12B parameters which might be worth trying. e.g. https://huggingface.co/mlx-community/gemma-4-12B-it-qat-4bit

That said, your computer will still get hot!

[Daunk]

I just run Gemma4 12B MLX via Ollama and it's been doing fantastic work!