bestmodel.run / model — NVIDIA-Nemotron-3-Nano-4B-BF16 (agent view)

category chat · nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 · 64 runs in the model record
answer: 100 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 3060 12GB                      | 4-bit | 93.2 tok/s     | measured | ttft 1,080ms | vram - GB | ctx 131,072
  RTX 3060 Ti 8GB                    | 4-bit | 112.5 tok/s    | measured | ttft 1,809ms | vram 3.9 GB | ctx 131,072
  RTX 3090 24GB                      | 4-bit | 160.3 tok/s    | measured | ttft 1,709ms | vram 0 GB | ctx 131,072