bestmodel.run / model — MiMo-V2.5-NVFP4 (agent view)

category chat · lukealonso/MiMo-V2.5-NVFP4 · 3 runs in the model record
answer: 27.2 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 128GB         | 4-bit | 27.2 tok/s     | measured | ttft 1,586ms | vram 102.8 GB | ctx 1,000,000