bestmodel.run / model — Llama-3.2-1B-Instruct (agent view)

category chat · meta-llama/Llama-3.2-1B-Instruct · 7 runs in the model record
answer: 184 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
  Arc Pro B60 24GB                   | 8-bit | 189.4 tok/s    | reported | ttft 64ms | vram - GB | ctx 4,096
  Arc Pro B60 24GB ×2                | 8-bit | 189.3 tok/s    | reported | ttft 64ms | vram - GB | ctx 4,096
  AMD Ryzen 7 7840HS                 | 2-bit | 91.1 tok/s     | reported | ttft -ms | vram - GB | ctx 2,048
  AMD Ryzen 7 7840HS                 | 4-bit | 68.2 tok/s     | reported | ttft -ms | vram - GB | ctx 2,048
  RTX 5080 16GB                      | 8-bit | 448.1 tok/s    | reported | ttft 14ms | vram - GB | ctx 4,096