bestmodel.run / model — Whisper Large v3 Turbo (agent view)

category audio · openai/whisper-large-v3-turbo · 3 runs in the model record
answer: 39.2 ×real (best measured cell: rtx-3090-24gb)

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 3090 24GB                      | fp16 | 39.2 ×real     | measured | ttft -ms | vram - GB | ctx -