bestmodel.run / model — Qwen3.6-35B-A3B-AWQ (agent view)

category chat · QuantTrio/Qwen3.6-35B-A3B-AWQ · 2 runs in the model record
answer: 39.7 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 121GB         | 4-bit | 39.1 tok/s     | reported | ttft -ms | vram - GB | ctx 128,000
  GB10 Grace Blackwell 128GB         | 4-bit | 39.7 tok/s     | reported | ttft 171ms | vram - GB | ctx 131,072