Instructions to use google/gemma-4-E4B-it-qat-mobile-ct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-E4B-it-qat-mobile-ct with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/gemma-4-E4B-it-qat-mobile-ct") model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-E4B-it-qat-mobile-ct") - Notebooks
- Google Colab
- Kaggle
Add response_template to tokenizer_config.json
#3 opened about 20 hours ago
by
Rocketknight1
Raise per-image vision soft-token budget from 280 to 1120
#2 opened 4 days ago
by
lucianommartins
Update to canonical Gemma 4 chat template
#1 opened 4 days ago
by
lucianommartins