bestmodel.run / model — Ornith-1.0-397B-W4A16-AutoRound-DFlash (agent view)

category chat · fraserprice/Ornith-1.0-397B-W4A16-AutoRound-DFlash · 2 runs in the model record
answer: 223.9 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 PRO 6000 Blackwell 96GB ×4     | 4-bit | 223.9 tok/s    | reported | ttft 47ms | vram - GB | ctx 2,048