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-ai-pro-r9700-32gb. Full machine surface: /llms.txt · REST API: api.bestmodel.run rig | model | basis | value | n radeon-ai-pro-r9700-32gb | qwen-qwen3-5-9b | reported | 371.8 tok/s | n=1 radeon-ai-pro-r9700-32gb | qwen-qwen3-8-27b | measured | 285.5 tok/s | n=7 radeon-ai-pro-r9700-32gb | qwen-qwen3-6-27b | reported | 278 tok/s | n=1 radeon-ai-pro-r9700-32gb | qwen-qwen3-6-35b-a3b | measured | 277.4 tok/s | n=5 radeon-ai-pro-r9700-32gb | qwen-qwen3-5-27b | reported | 196.2 tok/s | n=1 radeon-ai-pro-r9700-32gb | google-gemma-4-e2b-it | reported | 169.7 tok/s | n=1 radeon-ai-pro-r9700-32gb | google-gemma-4-e4b-it | reported | 137 tok/s | n=1 radeon-ai-pro-r9700-32gb | hauhaucs-qwen3-6-35b-a3b-uncensored-hauhaucs-aggressive | reported | 126.6 tok/s | n=1 radeon-ai-pro-r9700-32gb | bartowski-ling-3-0-tiny-gguf | reported | 113.4 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-gemma-4-26b-a4b-it | reported | 98 tok/s | n=1 radeon-ai-pro-r9700-32gb | google-gemma-4-e4b-it | reported | 96 tok/s | n=1 radeon-ai-pro-r9700-32gb | meta-models-muse-glimmer-30b-gguf | reported | 82.5 tok/s | n=2 radeon-ai-pro-r9700-32gb | unsloth-glm-4-7-flash-gguf | reported | 82.1 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-qwen3-6-35b-a3b-gguf | reported | 78.6 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-glm-4-7-flash-gguf | reported | 75.8 tok/s | n=1 radeon-ai-pro-r9700-32gb | deepseek-ai-deepseek-v4-flash-0731 | measured | 59.4 tok/s | n=3 radeon-ai-pro-r9700-32gb | unsloth-gemma-4-12b-it-gguf | reported | 58.2 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-qwen3-6-35b-a3b-mtp-gguf | reported | 56.7 tok/s | n=1 radeon-ai-pro-r9700-32gb | jackrong-qwopus3-6-27b-v2-mtp-gguf | measured | 53.9 tok/s | n=3 radeon-ai-pro-r9700-32gb | deepseek-ai-deepseek-v4-flash-0731 | reported | 50.5 tok/s | n=2 radeon-ai-pro-r9700-32gb | unsloth-qwen3-6-27b-mtp-gguf | reported | 43.3 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-qwen3-8-27b-gguf | measured | 41.2 tok/s | n=3 radeon-ai-pro-r9700-32gb | unsloth-qwen3-8-27b-gguf | measured | 39.5 tok/s | n=14 radeon-ai-pro-r9700-32gb | qwen-qwen3-8-27b | reported | 38.7 tok/s | n=2 radeon-ai-pro-r9700-32gb | unsloth-muse-glimmer-30b-gguf | reported | 33.2 tok/s | n=2 radeon-ai-pro-r9700-32gb | hauhaucs-qwen3-5-27b-uncensored-hauhaucs-aggressive | reported | 30.8 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-qwen3-6-27b-gguf | reported | 30.2 tok/s | n=2 radeon-ai-pro-r9700-32gb | unsloth-qwen3-5-27b | measured | 29.1 tok/s | n=5 radeon-ai-pro-r9700-32gb | google-gemma-4-31b-it | reported | 28.8 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-gemma-4-31b-it | reported | 27.6 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-qwen3-5-27b-gguf | reported | 26.7 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-muse-glimmer-30b-gguf | reported | 25.8 tok/s | n=2 radeon-ai-pro-r9700-32gb | unsloth-qwen3-8-flash-next-gguf | reported | 25.6 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-gemma-4-31b-it-gguf | reported | 25.4 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-qwen3-8-27b-gguf | measured | 21.6 tok/s | n=4 radeon-ai-pro-r9700-32gb | unsloth-glm-5-3-flash-gguf | reported | 17.4 tok/s | n=1 radeon-ai-pro-r9700-32gb | unsloth-glm-5-3-flash-gguf | reported | 16.6 tok/s | n=1 Capture or correct a number: /console (signed, Ed25519).