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=radeon-rx-7900-xtx-24gb.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  radeon-rx-7900-xtx-24gb            | unsloth-qwen3-6-35b-a3b                | reported | 104.5 tok/s    | n=1
  radeon-rx-7900-xtx-24gb            | jackrong-gemopus-4-26b-a4b-it-gguf     | reported | 94.5 tok/s     | n=1
  radeon-rx-7900-xtx-24gb            | unsloth-gemma-4-26b-a4b-it-gguf        | reported | 94.3 tok/s     | n=1
  radeon-rx-7900-xtx-24gb            | jackrong-qwen3-5-9b-claude-4-6-opus-reasoning-distilled-gguf | reported | 93.2 tok/s     | n=1
  radeon-rx-7900-xtx-24gb            | djlougen-ornstein3-6-35b-a3b-gguf      | reported | 62.4 tok/s     | n=1
  radeon-rx-7900-xtx-24gb            | unsloth-qwen3-6-35b-a3b-gguf           | reported | 57.6 tok/s     | n=1
  radeon-rx-7900-xtx-24gb            | cyberjuju-qwen3-30b-a3b-instruct-2507-awq-4bit-q4-k-m-gguf | reported | 47.8 tok/s     | n=1
  radeon-rx-7900-xtx-24gb            | lmstudio-community-qwen3-coder-30b-a3b-instruct-gguf | reported | 46.9 tok/s     | n=1
  radeon-rx-7900-xtx-24gb            | unsloth-qwen3-6-27b-gguf               | reported | 33.3 tok/s     | n=1
  radeon-rx-7900-xtx-24gb            | jackrong-qwopus3-5-27b-v3-gguf         | reported | 28.6 tok/s     | n=1
  radeon-rx-7900-xtx-24gb            | unsloth-qwen3-6-27b-gguf               | reported | 28.5 tok/s     | n=1
  radeon-rx-7900-xtx-24gb            | qwen-qwen3-6-27b                       | measured | 28.4 tok/s     | n=5

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