bestmodel.run / model — NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 (agent view)

category chat · nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 · 1 runs in the model record
answer: 135.1 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 | 38.7 tok/s     | reported | ttft -ms | vram - GB | ctx 262,144