bestmodel.run / model — Meta-Llama-3-8B-Instruct (agent view)

category chat · meta-llama/Meta-Llama-3-8B-Instruct · 31 runs in the model record
answer: 48.4 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                   | 4-bit | 43.1 tok/s     | measured | ttft 1,117ms | vram - GB | ctx 4,096
  Arc Pro B60 24GB ×2                | 4-bit | 46.7 tok/s     | measured | ttft 874ms | vram - GB | ctx 4,096
  RTX 5080 16GB                      | 4-bit | 129.5 tok/s    | measured | ttft 79ms | vram - GB | ctx 4,096