bestmodel.run / model — microsoft_Phi-4-mini-instruct-GGUF (agent view)

category chat · bartowski/microsoft_Phi-4-mini-instruct-GGUF · 2 runs in the model record
answer: 84.4 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
  Arc Pro B70 32GB                   | 4-bit | 96.6 tok/s     | reported | ttft 70ms | vram - GB | ctx 4,096
  Arc Pro B70 32GB                   | 8-bit | 72.3 tok/s     | reported | ttft 119ms | vram - GB | ctx 4,096