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=ryzen-ai-max-385-24gb.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  ryzen-ai-max-385-24gb              | unsloth-gemma-4-e2b-it-gguf            | measured | 35.2 tok/s     | n=3
  ryzen-ai-max-385-24gb              | unsloth-qwen3-30b-a3b-gguf             | measured | 30.7 tok/s     | n=3
  ryzen-ai-max-385-24gb              | unsloth-qwen3-coder-30b-a3b-instruct-gguf | reported | 30 tok/s       | n=2
  ryzen-ai-max-385-24gb              | openai-gpt-oss-20b                     | reported | 23.2 tok/s     | n=2
  ryzen-ai-max-385-24gb              | bartowski-nvidia-nemotron-cascade-2-30b-a3b-gguf | reported | 21.4 tok/s     | n=2
  ryzen-ai-max-385-24gb              | unsloth-qwen3-6-35b-a3b-gguf           | reported | 19.2 tok/s     | n=2
  ryzen-ai-max-385-24gb              | unsloth-gemma-4-e4b-it-gguf            | reported | 18.7 tok/s     | n=1
  ryzen-ai-max-385-24gb              | bartowski-google-gemma-4-e4b-it-gguf   | reported | 15.4 tok/s     | n=1
  ryzen-ai-max-385-24gb              | lmstudio-community-olmocr-2-7b-1025-gguf | reported | 14.9 tok/s     | n=1
  ryzen-ai-max-385-24gb              | unsloth-qwen3-vl-8b-instruct-gguf      | reported | 14.1 tok/s     | n=1
  ryzen-ai-max-385-24gb              | unsloth-gemma-4-12b-it-gguf            | reported | 8.6 tok/s      | n=1
  ryzen-ai-max-385-24gb              | unsloth-qwen3-5-27b-gguf               | reported | 4.1 tok/s      | n=2

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