bestmodel.run / model — DeepHermes-3-Mistral-24B-Preview (agent view)

category chat · NousResearch/DeepHermes-3-Mistral-24B-Preview · 31 runs in the model record
answer: 30.8 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
  RTX 3060 12GB ×2                   | 4-bit | 21.5 tok/s     | measured | ttft 4,738ms | vram 19.5 GB | ctx 131,072
  RTX 3090 24GB                      | 4-bit | 37.9 tok/s     | measured | ttft 3,582ms | vram - GB | ctx 131,072