Instructions to use google/gemma-4-E2B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-E2B-it with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/gemma-4-E2B-it") model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-E2B-it") - Notebooks
- Google Colab
- Kaggle
Appreciation Post
Just here to leave this appreciation post, a little late to the party, but credits where it's due.
Gemma 4 has been a huge leap in consistency, performance and design.
Absolute pleasure to work with, all the issues with the transformer library is ironed out, works well with all standard libraries, and that Mr. Jeff Dean's black magic has done wonders for Gemma.
Absolutely, and officially COOKED with this drop.
Please accept my most heartfelt congratulations.
Also a small ask: it would be nice to add all the models in their respective collections.
Wishing the team all the best in your future endeavors.
Hi @Maani -
Thanks for the feedback! The Gemma 4 family is organized into dedicated collections, covering Gemma 4, Gemma 4 QAT, and Gemma 4 QAT Mobile models:
Feel free to explore them, and if there's something specific you're looking for that you can't find, please let us know and we'll be happy to help.
@sonali-kumari11 thank you so much. I sure will be letting the team know if anything comes up. wishing you an amazing day!