bestmodel.run / model — Hermes-3-Llama-3.1-8B (agent view)

category chat · NousResearch/Hermes-3-Llama-3.1-8B · 5 runs in the model record
answer: 38.5 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 | 53.1 tok/s     | reported | ttft -ms | vram 7.7 GB | ctx 8,192
  GTX 1080 Ti 11GB                   | 5-bit | 38.2 tok/s     | reported | ttft -ms | vram 8.4 GB | ctx 8,192
  Ryzen AI Max 395 128GB             | 5-bit | 38.5 tok/s     | measured | ttft -ms | vram 7.8 GB | ctx 32,768