bestmodel.run / model — Llama-2-7b-hf (agent view)

category chat · meta-llama/Llama-2-7b-hf · 5 runs in the model record
answer: 50.4 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                   | 2-bit | 35.3 tok/s     | reported | ttft 367ms | vram - GB | ctx 4,096
  Arc Pro B60 24GB ×2                | 2-bit | 34.8 tok/s     | reported | ttft 367ms | vram - GB | ctx 4,096
  RTX 5080 16GB                      | 2-bit | 201.6 tok/s    | reported | ttft 81ms | vram - GB | ctx 4,096