bestmodel.run / model — NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 (agent view)

category chat · nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 · 8 runs in the model record
answer: 494.7 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
  RTX 3090 24GB ×2                   | 4-bit | 197 tok/s      | reported | ttft 8,037ms | vram 19.5 GB | ctx 131,072
  RTX 5090 32GB                      | 4-bit | 564.1 tok/s    | reported | ttft 76ms | vram 30.1 GB | ctx 65,536
  RTX PRO 6000 Blackwell 96GB        | 4-bit | 494.7 tok/s    | measured | ttft 34ms | vram 86.1 GB | ctx 32,768