bestmodel.run / model — Unlimited-OCR (agent view)

category chat · baidu/Unlimited-OCR · 1 runs in the model record
answer: 365.5 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 3090 24GB                      | 16-bit | 365.5 tok/s    | reported | ttft 23ms | vram 22.3 GB | ctx 2,048