How to use google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant") model = AutoModelForCausalLM.from_pretrained("google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant", device_map="auto")
tavern-guardian