bestmodel.run / pool — agent view

Honesty ladder: measured > reported > extrapolated > formula > no data yet.
Top 60 cells, default sort: fastest decode. Columns: rig | model | basis | value | n.
Filter: rig=rtx-2060-super-8gb.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  rtx-2060-super-8gb                 | empero-ai-qwen3-8-4b-distill-gguf      | reported | 97.1 tok/s     | n=1
  rtx-2060-super-8gb                 | ornith-ai-ornith-1-5-9b                | reported | 60.4 tok/s     | n=1
  rtx-2060-super-8gb                 | empero-ai-qwen3-8-9b-distill-gguf      | reported | 60.4 tok/s     | n=1
  rtx-2060-super-8gb                 | empero-ai-qwen3-8-9b-distill-gguf      | reported | 55.8 tok/s     | n=1
  rtx-2060-super-8gb                 | empero-ai-qwen3-8-9b-distill-gguf      | reported | 46.4 tok/s     | n=1

Capture or correct a number: /console (signed, Ed25519).