bestmodel.run / model — Olmo-3-32B-Think (agent view)

category chat · allenai/Olmo-3-32B-Think · 17 runs in the model record
answer: 16.4 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 3060 12GB ×2                   | 4-bit | 15.4 tok/s     | measured | ttft 10,913ms | vram 21 GB | ctx 65,536
  RTX 3090 24GB                      | 4-bit | 22.2 tok/s     | measured | ttft 9,216ms | vram - GB | ctx 131,072