bestmodel.run / model — Mistral-Medium-3.5-128B (agent view)

category chat · mistralai/Mistral-Medium-3.5-128B · 9 runs in the model record
answer: 6.5 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 | 6.4 tok/s      | measured | ttft 2,885ms | vram - GB | ctx 16,384