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-5000-16gb.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  rtx-5000-16gb                      | weiboai-vibethinker-3b                 | reported | 76.6 tok/s     | n=1
  rtx-5000-16gb                      | hauhaucs-gpt-oss-20b-uncensored-hauhaucs-aggressive | reported | 66.8 tok/s     | n=1
  rtx-5000-16gb                      | whiterabbitneo-llama-3-1-whiterabbitneo-2-8b | reported | 50.6 tok/s     | n=1
  rtx-5000-16gb                      | luisppb16-qwen3-5-9b-red-team          | reported | 35.9 tok/s     | n=1
  rtx-5000-16gb                      | hauhaucs-qwen3-5-9b-uncensored-hauhaucs-aggressive | reported | 33.4 tok/s     | n=1
  rtx-5000-16gb                      | davidau-qwen3-5-9b-claude-4-6-highiq-instruct-heretic-uncensored | reported | 31.5 tok/s     | n=2
  rtx-5000-16gb                      | uncensoredai-uncensoredlm-deepseek-r1-distill-qwen-14b | reported | 27 tok/s       | n=1
  rtx-5000-16gb                      | deepseek-ai-deepseek-r1-distill-qwen-14b | reported | 24.4 tok/s     | n=1
  rtx-5000-16gb                      | qwen-qwen2-5-coder-14b-instruct        | reported | 24.3 tok/s     | n=1
  rtx-5000-16gb                      | google-gemma-4-12b-it                  | reported | 23.4 tok/s     | n=1
  rtx-5000-16gb                      | google-gemma-4-12b-it                  | reported | 21.5 tok/s     | n=1

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