bestmodel.run / model — Hy3-GGUF (agent view)

category chat · AngelSlim/Hy3-GGUF · 5 runs in the model record
answer: 35.8 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
  CMP 170HX 64GB ×2                  | 2-bit | 34.9 tok/s     | measured | ttft -ms | vram 98.6 GB | ctx 32,768
  RTX 5090 32GB ×4                   | 1-bit | 87.1 tok/s     | reported | ttft 50ms | vram 121.6 GB | ctx 131,072