bestmodel.run / model — Qwen3.6-35B-A3B-Quark-W8A8-INT8 (agent view)

category chat · nameistoken/Qwen3.6-35B-A3B-Quark-W8A8-INT8 · 3 runs in the model record
answer: 93.6 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                | 8-bit | 85.9 tok/s     | reported | ttft 273ms | vram - GB | ctx 32,768
  Arc Pro B70 32GB ×4                | 8-bit | 96.5 tok/s     | reported | ttft 132ms | vram - GB | ctx 32,768