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-5060-ti-16gb.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  rtx-5060-ti-16gb                   | liquidai-lfm2-5-8b-a1b                 | reported | 254.3 tok/s    | n=1
  rtx-5060-ti-16gb                   | liquidai-lfm2-5-8b-a1b                 | reported | 183.1 tok/s    | n=1
  rtx-5060-ti-16gb                   | hackertwins-nvidia-nemotron-labs-3-elastic-23b-a2-8b-gguf | reported | 158.3 tok/s    | n=1
  rtx-5060-ti-16gb                   | unsloth-qwen3-6-35b-a3b-mtp-gguf       | reported | 119.1 tok/s    | n=2
  rtx-5060-ti-16gb                   | unsloth-gemma-4-26b-a4b-it-gguf        | reported | 103.4 tok/s    | n=2
  rtx-5060-ti-16gb                   | unsloth-gemma-4-12b-it-gguf            | reported | 51.3 tok/s     | n=1
  rtx-5060-ti-16gb                   | qwen-qwen3-6-27b                       | reported | 46 tok/s       | n=1
  rtx-5060-ti-16gb                   | unsloth-qwen3-6-35b-a3b-mtp-gguf       | reported | 36.7 tok/s     | n=1
  rtx-5060-ti-16gb                   | unsloth-qwen3-6-27b-mtp-gguf           | reported | 26.7 tok/s     | n=1

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