bestmodel.run / model — Qwen3-235B-A22B-Thinking-2507 (agent view)

category chat · Qwen/Qwen3-235B-A22B-Thinking-2507 · 4 runs in the model record
answer: 15.8 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
  GB10 Grace Blackwell 128GB         | 4-bit | 16 tok/s       | reported | ttft 170ms | vram - GB | ctx 32,768
  M3 Ultra 512GB                     | 4-bit | 15.6 tok/s     | measured | ttft 3,461ms | vram - GB | ctx 2,048