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-r9700-32gb-x2.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  radeon-ai-pro-r9700-32gb-x2        | unsloth-qwen3-8-27b-nvfp4              | measured | 229.4 tok/s    | n=3
  radeon-ai-pro-r9700-32gb-x2        | amd-qwen3-8-27b-quark-awq-mxfp4        | measured | 102.6 tok/s    | n=5
  radeon-ai-pro-r9700-32gb-x2        | google-gemma-4-26b-a4b-it              | measured | 99.3 tok/s     | n=4
  radeon-ai-pro-r9700-32gb-x2        | zai-org-glm-4-7-flash                  | reported | 92.9 tok/s     | n=1
  radeon-ai-pro-r9700-32gb-x2        | google-gemma-4-26b-a4b-it              | reported | 87.3 tok/s     | n=1
  radeon-ai-pro-r9700-32gb-x2        | qwen-qwen3-coder-next                  | reported | 80.8 tok/s     | n=1
  radeon-ai-pro-r9700-32gb-x2        | orcarouter-qwen3-8-27b-uncensored-gguf | reported | 51.8 tok/s     | n=1
  radeon-ai-pro-r9700-32gb-x2        | openai-gpt-oss-20b                     | reported | 48.3 tok/s     | n=1
  radeon-ai-pro-r9700-32gb-x2        | qwen-qwen3-8-27b                       | reported | 46.8 tok/s     | n=2
  radeon-ai-pro-r9700-32gb-x2        | qwen-qwen3-6-35b-a3b                   | reported | 32.6 tok/s     | n=2
  radeon-ai-pro-r9700-32gb-x2        | qwen-qwen3-32b                         | reported | 22.9 tok/s     | n=1

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