bestmodel.run / model — mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF (agent view)

category chat · bartowski/mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF · 1 runs in the model record
answer: 21.8 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 3060 12GB ×2                   | 4-bit | 21.8 tok/s     | reported | ttft -ms | vram 17.4 GB | ctx 65,536