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-pro-6000-blackwell-96gb-x4.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  rtx-pro-6000-blackwell-96gb-x4     | nvidia-qwen3-6-35b-a3b-nvfp4           | reported | 325.9 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | fraserprice-deepseek-v4-flash-abliterated-dspark | reported | 309 tok/s      | n=2
  rtx-pro-6000-blackwell-96gb-x4     | fraserprice-deepseek-v4-flash-dspark   | measured | 308.2 tok/s    | n=3
  rtx-pro-6000-blackwell-96gb-x4     | deepseek-ai-deepseek-v4-flash-0731     | measured | 296.7 tok/s    | n=5
  rtx-pro-6000-blackwell-96gb-x4     | deepseek-ai-deepseek-v4-flash-0731     | reported | 231.5 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | fraserprice-ornith-1-0-397b-w4a16-autoround-dflash | reported | 223.9 tok/s    | n=2
  rtx-pro-6000-blackwell-96gb-x4     | fraserprice-deepseek-v4-flash-abliterated | reported | 217.5 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | poolside-laguna-s-2-1-dflash-fp8       | reported | 209.9 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | poolside-laguna-s-2-1-dflash           | reported | 183.7 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | nvidia-qwen3-6-27b-nvfp4               | reported | 168.1 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | zai-org-glm-5-3-flash                  | reported | 146.8 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | qwen-qwen3-6-27b                       | reported | 146.1 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | google-gemma-4-12b-it                  | reported | 145.7 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | poolside-laguna-s-2-1                  | reported | 126.6 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | auroter-deepseek-v4-flash-0731-nvfp4   | reported | 118.2 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | pilcothink-ornith-1-0-397b-w4a16-autoround | reported | 116.3 tok/s    | n=1
  rtx-pro-6000-blackwell-96gb-x4     | google-gemma-4-31b-it                  | reported | 98.2 tok/s     | n=1
  rtx-pro-6000-blackwell-96gb-x4     | jacklarmer-glm-5-2-abliterated-mxfp8-nvfp4-nf3-hybrid | reported | 92 tok/s       | n=1
  rtx-pro-6000-blackwell-96gb-x4     | madeby561-glm-5-2-nvfp4-reap-504b-term | measured | 86.8 tok/s     | n=3
  rtx-pro-6000-blackwell-96gb-x4     | madeby561-glm-5-2-mxfp8-nvfp4-nf3-hybrid | reported | 74.4 tok/s     | n=2
  rtx-pro-6000-blackwell-96gb-x4     | madeby561-glm-5-2-mxfp8-nvfp4-nf3-hybrid | reported | 68.4 tok/s     | n=2
  rtx-pro-6000-blackwell-96gb-x4     | 0xsero-glm-5-2-504b-nvidia             | reported | 52.6 tok/s     | n=1
  rtx-pro-6000-blackwell-96gb-x4     | huihui-ai-huihui-glm-5-2-abliterated-gguf | reported | 47.9 tok/s     | n=1
  rtx-pro-6000-blackwell-96gb-x4     | unsloth-glm-5-2-gguf                   | reported | 39.7 tok/s     | n=2

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