bestmodel.run / model — gemma-3-4b-it (agent view)

category chat · google/gemma-3-4b-it · 2 runs in the model record
answer: 112.1 tok/s (model median)

Honesty ladder: measured > reported > extrapolated > formula > no data yet.
Empty fields stay empty — never filled with an estimate.

  rig | quant | median result | basis | ttft | peak vram | max context
  M3 Ultra 512GB                     | 4-bit | 127.2 tok/s    | reported | ttft 185ms | vram - GB | ctx 8,192
  RTX 3060 12GB                      | 4-bit | 97 tok/s       | reported | ttft 1,063ms | vram 4.9 GB | ctx 4,608