bestmodel.run / model — MiniMax-M2.7 (agent view)

category chat · MiniMaxAI/MiniMax-M2.7 · 34 runs in the model record
answer: 32.2 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
  Arc Pro B70 32GB ×4                | 4-bit | 37.7 tok/s     | measured | ttft -ms | vram 29.2 GB | ctx 24,576
  GB10 Grace Blackwell 128GB         | 4-bit | 30.9 tok/s     | reported | ttft 807ms | vram 117 GB | ctx 108,000
  Radeon AI Pro R9700 32GB ×3        | 4-bit | 25.2 tok/s     | measured | ttft 771ms | vram - GB | ctx 32,768