bestmodel.run / model — SmolLM2-360M-Instruct (agent view)

category chat · HuggingFaceTB/SmolLM2-360M-Instruct · 5 runs in the model record
answer: 208 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 Ryzen 7 7840HS                 | 2-bit | 208 tok/s      | reported | ttft -ms | vram - GB | ctx 2,048
  AMD Ryzen 7 7840HS                 | 4-bit | 171.8 tok/s    | reported | ttft -ms | vram - GB | ctx 2,048
  AMD Ryzen 7 7840HS                 | 8-bit | 130.6 tok/s    | reported | ttft -ms | vram - GB | ctx 2,048
  RTX 3060 12GB                      | 8-bit | 437 tok/s      | reported | ttft 229ms | vram 1.9 GB | ctx 4,608
  RTX PRO 6000 Blackwell 96GB        | 8-bit | 968.1 tok/s    | reported | ttft -ms | vram 1.1 GB | ctx 4,608