bestmodel.run / model — Kimi-Dev-72B (agent view)

category chat · moonshotai/Kimi-Dev-72B · 1 runs in the model record
answer: 13.5 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
  Radeon AI Pro R9700 32GB ×3        | 4-bit | 11.4 tok/s     | reported | ttft 259ms | vram - GB | ctx 65,536