bestmodel.run / model — NVIDIA-Nemotron-Nano-12B-v2 (agent view)

category chat · nvidia/NVIDIA-Nemotron-Nano-12B-v2 · 18 runs in the model record
answer: 47 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 | 39 tok/s       | measured | ttft 7,700ms | vram 9.9 GB | ctx 131,072
  RTX 3090 24GB                      | 4-bit | 55.8 tok/s     | measured | ttft 3,857ms | vram - GB | ctx 131,072