How to use lmstudio-community/gemma-4-12B-it-MLX-8bit with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("lmstudio-community/gemma-4-12B-it-MLX-8bit") model = AutoModelForMultimodalLM.from_pretrained("lmstudio-community/gemma-4-12B-it-MLX-8bit", device_map="auto")
How to use lmstudio-community/gemma-4-12B-it-MLX-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gemma-4-12B-it-MLX-8bit lmstudio-community/gemma-4-12B-it-MLX-8bit
