bestmodel.run / model — Grug-12B-GGUF (agent view)

category chat · kai-os/Grug-12B-GGUF · 2 runs in the model record
answer: 42.4 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 5070 12GB                      | 4-bit | 69.2 tok/s     | reported | ttft 168ms | vram - GB | ctx 2,048
  RX 7700 XT 12GB                    | 4-bit | 15.5 tok/s     | reported | ttft 599ms | vram - GB | ctx 2,048