bestmodel.run / model — nvidia_Nemotron-Cascade-8B-GGUF (agent view)

category chat · bartowski/nvidia_Nemotron-Cascade-8B-GGUF · 8 runs in the model record
answer: 47.5 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 | 47.5 tok/s     | measured | ttft 2,183ms | vram 11.2 GB | ctx 131,072