OraCore · Topic ·tools

Gemma 4 assistant models get faster draft tokens

Gemma 4 E2B and E4B assistant models use centroid masking to cut lm_head work about 45x with little quality loss.

1 articles in this thread ·Last updated 19h ago·First seen Jul 5, 2026

Timeline

  1. Gemma 4 assistant models get faster draft tokens seed

    Gemma 4 E2B and E4B assistant models use centroid masking to cut lm_head work about 45x with little quality loss.