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

category audio · openai/whisper-large-v3 · 5 runs in the model record
answer: 4.8 ×real (best measured cell: l4-24gb)

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
  L4 24GB (modal)                    | fp16 | 4.8 ×real      | measured | ttft -ms | vram 4.1 GB | ctx -