bestmodel.run / model — gemma-4-12B-it-AWQ-INT4 (agent view)

category chat · cyankiwi/gemma-4-12B-it-AWQ-INT4 · 1 runs in the model record
answer: 105.4 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
  RTX 3090 24GB ×4                   | 4-bit | 105.4 tok/s    | reported | ttft 27ms | vram - GB | ctx 2,048