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=arc-pro-b60-24gb.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  arc-pro-b60-24gb                   | meta-llama-llama-3-2-1b-instruct       | reported | 189.4 tok/s    | n=2
  arc-pro-b60-24gb                   | frosty40-quest-30b-rl-b70-turbo-gguf   | reported | 77.2 tok/s     | n=1
  arc-pro-b60-24gb                   | qwen-qwen3-4b                          | reported | 76 tok/s       | n=2
  arc-pro-b60-24gb                   | poolside-laguna-xs-2-1                 | reported | 72.5 tok/s     | n=1
  arc-pro-b60-24gb                   | ornith-ai-ornith-1-0-35b-gguf          | reported | 62.7 tok/s     | n=2
  arc-pro-b60-24gb                   | meta-llama-meta-llama-3-8b-instruct    | measured | 43.1 tok/s     | n=12
  arc-pro-b60-24gb                   | qwen-qwen3-6-35b-a3b                   | reported | 42.6 tok/s     | n=2
  arc-pro-b60-24gb                   | openai-gpt-oss-20b                     | reported | 40.7 tok/s     | n=2
  arc-pro-b60-24gb                   | meta-llama-llama-2-7b-hf               | reported | 35.3 tok/s     | n=2
  arc-pro-b60-24gb                   | qwen-qwen3-5-9b                        | reported | 30.4 tok/s     | n=2
  arc-pro-b60-24gb                   | llmfan46-qwen3-6-35b-a3b-uncensored-heretic-native-mtp-preserved-gptq-int4 | reported | 25.4 tok/s     | n=1
  arc-pro-b60-24gb                   | unsloth-qwen3-8-27b-gguf               | reported | 21.2 tok/s     | n=1
  arc-pro-b60-24gb                   | unsloth-qwen3-8-27b-gguf               | reported | 16 tok/s       | n=1

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