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=m5-pro-24gb. Full machine surface: /llms.txt · REST API: api.bestmodel.run rig | model | basis | value | n m5-pro-24gb | liquidai-lfm2-5-1-2b-instruct-gguf | reported | 267.8 tok/s | n=1 m5-pro-24gb | abiray-minicpm5-1b-gguf | reported | 198.2 tok/s | n=1 m5-pro-24gb | lmstudio-community-lfm2-5-1-2b-instruct-gguf | reported | 186 tok/s | n=1 m5-pro-24gb | unsloth-gemma-4-26b-a4b-it-qat-gguf | reported | 121.6 tok/s | n=1 m5-pro-24gb | jetbrains-mellum2-12b-a2-5b-thinking-gguf-q4-k-m | reported | 112.3 tok/s | n=1 m5-pro-24gb | jetbrains-mellum2-12b-a2-5b-thinking-gguf-q8-0 | reported | 86.2 tok/s | n=1 m5-pro-24gb | unsloth-qwen3-6-35b-a3b-mtp-gguf | reported | 80.4 tok/s | n=2 m5-pro-24gb | unsloth-gemma-4-e2b-it-gguf | reported | 77.4 tok/s | n=1 m5-pro-24gb | unsloth-gpt-oss-20b-gguf | reported | 69.5 tok/s | n=1 m5-pro-24gb | unsloth-gemma-4-12b-it-qat-gguf | reported | 67.2 tok/s | n=1 m5-pro-24gb | unsloth-nvidia-nemotron-3-nano-4b-gguf | reported | 63.2 tok/s | n=1 m5-pro-24gb | unsloth-gemma-4-26b-a4b-it-gguf | reported | 55 tok/s | n=1 m5-pro-24gb | lmstudio-community-nvidia-nemotron-3-nano-4b-gguf | reported | 53.8 tok/s | n=1 m5-pro-24gb | unsloth-qwen3-5-9b-mtp-gguf | reported | 45.3 tok/s | n=1 m5-pro-24gb | unsloth-gemma-4-31b-it-qat-gguf | reported | 27.8 tok/s | n=1 m5-pro-24gb | unsloth-granite-4-1-8b-gguf | reported | 26.5 tok/s | n=1 m5-pro-24gb | unsloth-qwen3-6-27b-mtp-gguf | reported | 21.5 tok/s | n=1 m5-pro-24gb | unsloth-qwen3-6-27b-mtp-gguf | reported | 20 tok/s | n=2 m5-pro-24gb | unsloth-qwen3-6-27b-mtp-gguf | measured | 18.2 tok/s | n=3 Capture or correct a number: /console (signed, Ed25519).