bestmodel.run / model — Ministral-3-14B-Reasoning-2512-GGUF (agent view)

category chat · mistralai/Ministral-3-14B-Reasoning-2512-GGUF · 1 runs in the model record
answer: 89.4 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
  RTX 5090 32GB                      | 8-bit | 89.4 tok/s     | reported | ttft 47ms | vram - GB | ctx 2,048