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-3090-24gb-x4.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  rtx-3090-24gb-x4                   | cyankiwi-qwen3-5-122b-a10b-awq-4bit    | reported | 123.1 tok/s    | n=2
  rtx-3090-24gb-x4                   | cyankiwi-gemma-4-12b-it-awq-int4       | reported | 105.4 tok/s    | n=1
  rtx-3090-24gb-x4                   | cyankiwi-qwen3-6-27b-awq-bf16-int4     | reported | 67.1 tok/s     | n=1
  rtx-3090-24gb-x4                   | unsloth-qwen3-5-122b-a10b              | reported | 51.3 tok/s     | n=1
  rtx-3090-24gb-x4                   | nvidia-nvidia-nemotron-3-super-120b-a12b-nvfp4 | reported | 50.9 tok/s     | n=2
  rtx-3090-24gb-x4                   | unsloth-nvidia-nemotron-3-super-120b-a12b-gguf | measured | 49.7 tok/s     | n=3
  rtx-3090-24gb-x4                   | unsloth-deepseek-v4-flash-0731-gguf    | reported | 41 tok/s       | n=2
  rtx-3090-24gb-x4                   | deepseek-ai-deepseek-v4-flash          | reported | 35.3 tok/s     | n=1

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