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

category chat · RedHatAI/Qwen3.6-35B-A3B-NVFP4 · 5 runs in the model record
answer: 102.1 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 | 94.8 tok/s     | measured | ttft 153ms | vram 87 GB | ctx 262,144
  RTX 5090 32GB                      | 4-bit | 183.3 tok/s    | reported | ttft 122ms | vram 31.3 GB | ctx 262,144
  RTX 5090 32GB ×2                   | 4-bit | 340.8 tok/s    | reported | ttft 1,111ms | vram 58.9 GB | ctx 32,768