bestmodel.run / model — NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 (agent view)

category chat · nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · 12 runs in the model record
answer: 93 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                   | 4-bit | 93 tok/s       | measured | ttft -ms | vram - GB | ctx 16,384
  H100 80GB                          | 16-bit | 381.2 tok/s    | reported | ttft 68ms | vram 72.4 GB | ctx 32,768
  H200 SXM 141GB                     | 16-bit | 337.6 tok/s    | reported | ttft 56ms | vram 127.8 GB | ctx 32,768