google
/

gemma-4-E2B-it-qat-mobile-transformers

8-bit precision

Model card Files Files and versions

Resources

View closed (3)

How do we use MTP for speculative decoding?

#6 opened 20 minutes ago by

Add response_template to tokenizer_config.json

#3 opened 5 days ago by

Raise per-image vision soft-token budget from 280 to 1120

#2 opened 7 days ago by

lucianommartins