bestmodel.run / model — MobileLLM-350M (agent view)

category chat · facebook/MobileLLM-350M · 2 runs in the model record
answer: 714.4 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 3060 12GB                      | 8-bit | 448.1 tok/s    | reported | ttft 229ms | vram 1.8 GB | ctx 4,608
  RTX PRO 6000 Blackwell 96GB        | 8-bit | 980.8 tok/s    | reported | ttft -ms | vram 1 GB | ctx 4,608