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=radeon-ai-pro-r9700-57gb.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  radeon-ai-pro-r9700-57gb           | google-gemma-4-e2b-it                  | reported | 47.4 tok/s     | n=1
  radeon-ai-pro-r9700-57gb           | qwen-qwen3-6-35b-a3b                   | reported | 33.2 tok/s     | n=1
  radeon-ai-pro-r9700-57gb           | qwen-qwen3-6-35b-a3b                   | reported | 26.4 tok/s     | n=2
  radeon-ai-pro-r9700-57gb           | google-gemma-4-e4b-it                  | reported | 25.3 tok/s     | n=1
  radeon-ai-pro-r9700-57gb           | qwen-qwen3-6-35b-a3b                   | reported | 24.4 tok/s     | n=2
  radeon-ai-pro-r9700-57gb           | qwen-qwen3-5-9b                        | reported | 15.8 tok/s     | n=1
  radeon-ai-pro-r9700-57gb           | qwen-qwen3-6-27b                       | reported | 3.6 tok/s      | n=1
  radeon-ai-pro-r9700-57gb           | google-gemma-4-31b-it                  | reported | 3.3 tok/s      | n=1
  radeon-ai-pro-r9700-57gb           | qwen-qwen3-32b                         | reported | 3.2 tok/s      | n=1

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