bestmodel.run / model — Ornith-1.0-35B-NVFP4A16 (agent view)

category chat · palmfuture/Ornith-1.0-35B-NVFP4A16 · 1 runs in the model record
answer: 205 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 5090 32GB ×2                   | 4-bit | 205 tok/s      | reported | ttft 664ms | vram - GB | ctx 262,144