bestmodel.run / model — Llama-3.1-8B-Instruct (agent view)

category chat · meta-llama/Llama-3.1-8B-Instruct · 8 runs in the model record
answer: 76 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
  GTX 1080 Ti 11GB                   | 4-bit | 52.8 tok/s     | reported | ttft -ms | vram 7.7 GB | ctx 8,192
  GTX 1080 Ti 11GB                   | 5-bit | 38.1 tok/s     | reported | ttft -ms | vram 8.4 GB | ctx 8,192
  RTX 2080 8GB                       | 4-bit | 76 tok/s       | reported | ttft -ms | vram 4.9 GB | ctx 2,048
  RTX 3060 12GB                      | 4-bit | 76 tok/s       | reported | ttft -ms | vram 4.9 GB | ctx 2,048
  RTX 3080 12GB                      | 4-bit | 134 tok/s      | reported | ttft -ms | vram 5.1 GB | ctx 2,048
  RTX3060+RTX2080-pooled-20GB 20GB   | 4-bit | 105 tok/s      | reported | ttft -ms | vram 5 GB | ctx 2,048