bestmodel.run / model — Llama-3.1-8B-Instruct-FP8 (agent view)

category chat · nvidia/Llama-3.1-8B-Instruct-FP8 · 1 runs in the model record
answer: 158.1 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        | 8-bit | 158.1 tok/s    | reported | ttft -ms | vram - GB | ctx 32,768