bestmodel.run / model — olmOCR-2-7B-1025-GGUF (agent view)

category chat · lmstudio-community/olmOCR-2-7B-1025-GGUF · 3 runs in the model record
answer: 14.9 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
  GB10 Grace Blackwell 128GB         | 4-bit | 41.6 tok/s     | reported | ttft -ms | vram - GB | ctx 8,192
  Radeon 890M 32GB                   | 4-bit | 14.9 tok/s     | reported | ttft 1,400ms | vram - GB | ctx 2,048
  Ryzen AI Max 385 24GB              | 4-bit | 14.9 tok/s     | reported | ttft 1,400ms | vram - GB | ctx 2,048