bestmodel.run / model — MiniMax-M2.5-NVFP4 (agent view)

category chat · lukealonso/MiniMax-M2.5-NVFP4 · 1 runs in the model record
answer: 17.7 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
  GB10 Grace Blackwell 256GB         | 4-bit | 17.7 tok/s     | reported | ttft 42,303ms | vram - GB | ctx 196,608