bestmodel.run / model — NVIDIA-Nemotron-Nano-9B-v2 (agent view)

category chat · nvidia/NVIDIA-Nemotron-Nano-9B-v2 · 22 runs in the model record
answer: 64.3 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 ×2                   | 4-bit | 45.2 tok/s     | measured | ttft 6,144ms | vram 8.6 GB | ctx 131,072
  RTX 3060 + RTX 2080 20GB           | 4-bit | 50 tok/s       | reported | ttft -ms | vram 5.2 GB | ctx 2,048
  RTX 3060 Ti 8GB                    | 4-bit | 64.3 tok/s     | reported | ttft 292ms | vram - GB | ctx 2,048
  RTX 3080 12GB                      | 4-bit | 98 tok/s       | reported | ttft -ms | vram 5.2 GB | ctx 2,048
  RTX 3090 24GB                      | 4-bit | 73.7 tok/s     | measured | ttft 3,388ms | vram - GB | ctx 131,072