bestmodel.run / model — NVIDIA-Nemotron-3-Super-120B-A12B-GGUF (agent view)

category chat · unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF · 3 runs in the model record
answer: 49.7 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 3090 24GB ×4                   | 4-bit | 49.7 tok/s     | measured | ttft -ms | vram 21 GB | ctx 65,536