How to use google/gemma-4-E4B-it-qat-w4a16-ct with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/gemma-4-E4B-it-qat-w4a16-ct") model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-E4B-it-qat-w4a16-ct", device_map="auto")
lucianommartins 
gaurangblaze