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

category chat · XiaomiMiMo/MiMo-V2.5 · 5 runs in the model record
answer: 32.8 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        | 2-bit | 33.2 tok/s     | measured | ttft 11,694ms | vram - GB | ctx 32,768
  Ryzen AI Max 395 128GB             | 2-bit | 28.1 tok/s     | reported | ttft 3,919ms | vram - GB | ctx 768