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-a5000-24gb. Full machine surface: /llms.txt · REST API: api.bestmodel.run rig | model | basis | value | n rtx-a5000-24gb | ggml-org-gemma-3-1b-it-gguf | reported | 325.2 tok/s | n=2 rtx-a5000-24gb | qwen-qwen2-5-1-5b-instruct-gguf | reported | 320.6 tok/s | n=2 rtx-a5000-24gb | ggml-org-gemma-3-1b-it-gguf | reported | 281.9 tok/s | n=2 rtx-a5000-24gb | qwen-qwen2-5-1-5b-instruct-gguf | reported | 268 tok/s | n=2 rtx-a5000-24gb | bartowski-qwen-qwen3-5-2b-gguf | reported | 254.4 tok/s | n=2 rtx-a5000-24gb | ggml-org-gemma-4-e4b-it-gguf | reported | 121 tok/s | n=2 rtx-a5000-24gb | ggml-org-gemma-4-e4b-it-gguf | reported | 95.3 tok/s | n=2 rtx-a5000-24gb | unsloth-qwen3-6-27b-gguf | reported | 32.3 tok/s | n=2 Capture or correct a number: /console (signed, Ed25519).