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-5080-16gb.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  rtx-5080-16gb                      | meta-llama-llama-3-2-1b-instruct       | reported | 448.1 tok/s    | n=1
  rtx-5080-16gb                      | openai-gpt-oss-20b                     | reported | 222.4 tok/s    | n=1
  rtx-5080-16gb                      | meta-llama-llama-2-7b-hf               | reported | 201.6 tok/s    | n=1
  rtx-5080-16gb                      | ggml-org-gpt-oss-20b-gguf              | reported | 197.4 tok/s    | n=1
  rtx-5080-16gb                      | qwen-qwen3-6-35b-a3b                   | reported | 150.6 tok/s    | n=1
  rtx-5080-16gb                      | meta-llama-meta-llama-3-8b-instruct    | measured | 129.5 tok/s    | n=6
  rtx-5080-16gb                      | qwen-qwen3-5-9b                        | reported | 79.6 tok/s     | n=1
  rtx-5080-16gb                      | qwen-qwen3-30b-a3b-instruct-2507       | measured | 55.1 tok/s     | n=3

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