bestmodel.run / model — Ling-3.0-tiny (agent view)

category chat · inclusionAI/Ling-3.0-tiny · 4 runs in the model record
answer: 128.8 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
  AMD BC-250                         | 8-bit | 88.8 tok/s     | reported | ttft 2,021ms | vram - GB | ctx 2,048
  RTX 3060 12GB                      | 4-bit | 104.8 tok/s    | reported | ttft 137,729ms | vram 7.7 GB | ctx 262,144
  RTX PRO 6000 Blackwell 96GB        | 4-bit | 369.1 tok/s    | reported | ttft -ms | vram - GB | ctx 640