bestmodel.run / model — Devstral-Small-2-24B-Instruct-2512 (agent view)

category chat · mistralai/Devstral-Small-2-24B-Instruct-2512 · 1 runs in the model record
answer: 23.7 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        | 8-bit | 23.9 tok/s     | reported | ttft 244ms | vram - GB | ctx 24,576