bestmodel.run / model — OpenReasoning-Nemotron-7B-GGUF (agent view)

category chat · lmstudio-community/OpenReasoning-Nemotron-7B-GGUF · 53 runs in the model record
answer: 59.3 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                      | 4-bit | 57.3 tok/s     | measured | ttft 1,248ms | vram - GB | ctx 131,072
  RTX 3060 12GB ×2                   | 4-bit | 59.8 tok/s     | measured | ttft 2,567ms | vram 7.3 GB | ctx 131,072
  RTX 3060 Ti 8GB                    | 4-bit | 68.1 tok/s     | measured | ttft 2,139ms | vram 6.7 GB | ctx 131,072