bestmodel.run / model — models-moved (agent view)

category chat · ggml-org/models-moved · 2 runs in the model record
answer: 10,550.8 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
  AMD Ryzen 7 9800X3D                | 3-bit | 16,740.7 tok/s | reported | ttft 42ms | vram - GB | ctx 2,048
  RTX 5090 32GB                      | 3-bit | 4,360.9 tok/s  | reported | ttft 1ms | vram - GB | ctx 2,048