bestmodel.run / model — Ornstein3.6-35B-A3B-GGUF (agent view)

category chat · DJLougen/Ornstein3.6-35B-A3B-GGUF · 2 runs in the model record
answer: 100.2 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
  Radeon RX 7900 XTX 24GB            | 4-bit | 62.4 tok/s     | reported | ttft -ms | vram - GB | ctx 640
  RTX 3090 24GB ×2                   | 4-bit | 138 tok/s      | reported | ttft -ms | vram - GB | ctx 8,192