bestmodel.run / model — Ministral-3-3B-Instruct-2512 (agent view)

category chat · mistralai/Ministral-3-3B-Instruct-2512 · 29 runs in the model record
answer: 73.2 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
  GTX 1080 Ti 11GB                   | 4-bit | 94.9 tok/s     | reported | ttft -ms | vram 5.3 GB | ctx 8,192
  RTX 3060 12GB                      | 4-bit | 73.2 tok/s     | measured | ttft 721ms | vram - GB | ctx 131,072
  RTX 3060 12GB                      | 8-bit | 78 tok/s       | reported | ttft 990ms | vram 5.7 GB | ctx 4,608