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

  rig                               | model                                  | basis    | value          | n
  rtx-5060-ti-16gb-x2                | unsloth-qwen3-6-35b-a3b-mtp-gguf       | reported | 129.1 tok/s    | n=1
  rtx-5060-ti-16gb-x2                | unsloth-qwen3-6-35b-a3b-gguf           | reported | 94.4 tok/s     | n=1
  rtx-5060-ti-16gb-x2                | jiunsong-supergemma4-26b-uncensored-gguf-v2 | reported | 89.4 tok/s     | n=1
  rtx-5060-ti-16gb-x2                | lorbus-qwen3-6-27b-int4-autoround      | reported | 69.3 tok/s     | n=2
  rtx-5060-ti-16gb-x2                | qwen-qwen3-8-27b                       | measured | 63.2 tok/s     | n=3
  rtx-5060-ti-16gb-x2                | cyankiwi-qwen3-6-27b-awq-int4          | reported | 46.5 tok/s     | n=2
  rtx-5060-ti-16gb-x2                | unsloth-qwen3-6-27b-mtp-gguf           | reported | 33.3 tok/s     | n=2
  rtx-5060-ti-16gb-x2                | unsloth-qwen3-6-27b-gguf               | reported | 22.3 tok/s     | n=1
  rtx-5060-ti-16gb-x2                | nvidia-qwen3-6-27b-nvfp4               | reported | 15.9 tok/s     | n=1

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