bestmodel.run / model — gpt-oss-120b (agent view)

category chat · openai/gpt-oss-120b · 14 runs in the model record
answer: 72.6 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
  Arc Pro B70 32GB ×2                | 4-bit | 59.4 tok/s     | reported | ttft -ms | vram 60 GB | ctx 2,048
  GB10 Grace Blackwell 128GB         | 4-bit | 34.4 tok/s     | reported | ttft -ms | vram - GB | ctx 32,768
  Radeon AI Pro R9700 32GB ×3        | 16-bit | 69.9 tok/s     | measured | ttft 691ms | vram 68.5 GB | ctx 845
  RTX PRO 6000 Blackwell 96GB        | 16-bit | 196 tok/s      | measured | ttft 585ms | vram - GB | ctx 15,964
  RTX PRO 6000 Blackwell Workstation Edition 96GB | 4-bit | 197.3 tok/s    | measured | ttft 80ms | vram 86.3 GB | ctx 131,072
  Ryzen AI Max 395 128GB             | 16-bit | 38.8 tok/s     | reported | ttft 1,718ms | vram - GB | ctx 845