bestmodel.run / model — Qwen3.6-35B-A3B-NVFP4 (agent view)

category chat · mmangkad/Qwen3.6-35B-A3B-NVFP4 · 1 runs in the model record
answer: 506.2 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
  RTX PRO 6000 Blackwell 96GB        | 4-bit | 506.2 tok/s    | reported | ttft 113ms | vram 33.6 GB | ctx 8,192