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

category chat · unsloth/Phi-4-mini-reasoning-GGUF · 47 runs in the model record
answer: 74.3 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 | 65.2 tok/s     | measured | ttft 781ms | vram - GB | ctx 131,072
  RTX 3060 12GB ×2                   | 4-bit | 73.3 tok/s     | measured | ttft 1,838ms | vram 8.6 GB | ctx 131,072
  RTX 3090 24GB                      | 4-bit | 121.6 tok/s    | measured | ttft 1,403ms | vram - GB | ctx 131,072
  Ryzen AI Max 395 64GB              | 4-bit | 73.9 tok/s     | reported | ttft 515ms | vram 3.9 GB | ctx 8,192