How to use harishkumar12k/gemma-4-E2B-it-mlx-2Bit with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("harishkumar12k/gemma-4-E2B-it-mlx-2Bit") model = AutoModelForImageTextToText.from_pretrained("harishkumar12k/gemma-4-E2B-it-mlx-2Bit")
How to use harishkumar12k/gemma-4-E2B-it-mlx-2Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gemma-4-E2B-it-mlx-2Bit harishkumar12k/gemma-4-E2B-it-mlx-2Bit
