bestmodel.run / model — Devstral-Small-2505 (agent view)

category chat · mistralai/Devstral-Small-2505 · 1 runs in the model record
answer: 39.4 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
  M3 Ultra 512GB                     | 4-bit | 39.4 tok/s     | reported | ttft 126ms | vram - GB | ctx 8,192