bestmodel.run / model — Phi-4-reasoning (agent view)

category chat · microsoft/Phi-4-reasoning · 26 runs in the model record
answer: 31.4 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 3060 12GB ×2                   | 4-bit | 28.1 tok/s     | measured | ttft 2,476ms | vram 17.2 GB | ctx 131,072
  RTX 3090 24GB                      | 4-bit | 41.2 tok/s     | measured | ttft -ms | vram - GB | ctx 131,072