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

category chat · microsoft/Phi-4-reasoning-plus · 3 runs in the model record
answer: 32.7 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                      | 4-bit | 32.7 tok/s     | measured | ttft 2,478ms | vram - GB | ctx 4,096