bestmodel.run / model — Nemotron-Cascade-14B-Thinking (agent view)

category chat · nvidia/Nemotron-Cascade-14B-Thinking · 18 runs in the model record
answer: 34.2 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 | 29.7 tok/s     | measured | ttft 3,817ms | vram 15.4 GB | ctx 131,072
  RTX 3090 24GB                      | 4-bit | 44.5 tok/s     | measured | ttft 2,668ms | vram - GB | ctx 131,072