bestmodel.run / model — gemma-4-26B-A4B-it-AWQ-4bit (agent view)

category chat · cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit · 4 runs in the model record
answer: 369 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 5090 32GB                      | 4-bit | 369 tok/s      | measured | ttft 25ms | vram - GB | ctx 2,048