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-3090-ti-24gb.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  rtx-3090-ti-24gb                   | unsloth-qwen3-6-27b                    | reported | 155.9 tok/s    | n=1
  rtx-3090-ti-24gb                   | qwen-qwen3-6-27b                       | reported | 140.3 tok/s    | n=1
  rtx-3090-ti-24gb                   | qwen-qwen3-8b                          | reported | 133 tok/s      | n=1
  rtx-3090-ti-24gb                   | qwen-qwen3-5-9b                        | reported | 119.1 tok/s    | n=1
  rtx-3090-ti-24gb                   | jakeatx-qwen3-8-27b-atx-iq4-xs-m-gguf  | reported | 107.9 tok/s    | n=1
  rtx-3090-ti-24gb                   | unsloth-qwen3-6-27b-gguf               | measured | 35.7 tok/s     | n=3

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