google
/

gemma-4-E2B-it-assistant

gemma4_assistant

text-generation

Model card Files Files and versions

Resources

View closed (1)

Up to 4.23x faster inference with a DSpark draft model for gemma-4-E2B-it (167 --> 709 tokens/s; beats MTP on 7/9 benchmarks)

#3 opened 14 days ago by

Up to 3.74x faster inference with a DFlash2 speculative decoding draft model for gemma-4-E2B-it (167 --> 626 tokens/s)

#2 opened about 1 month ago by