bestmodel.run / model — Llama-3.2-3B-Instruct (agent view)

category chat · meta-llama/Llama-3.2-3B-Instruct · 45 runs in the model record
answer: 75.9 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
  M1 Max 64GB                        | 16-bit | 50.9 tok/s     | reported | ttft -ms | vram - GB | ctx 640
  RTX 3060 12GB                      | 4-bit | 95.8 tok/s     | measured | ttft 681ms | vram - GB | ctx 131,072
  RTX PRO 6000 Blackwell 96GB        | 4-bit | 489.2 tok/s    | reported | ttft -ms | vram 2.6 GB | ctx 640
  RX 6700 XT 12GB                    | 16-bit | 48.3 tok/s     | measured | ttft -ms | vram - GB | ctx 4,736