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-pro-6000-blackwell-96gb. Full machine surface: /llms.txt · REST API: api.bestmodel.run rig | model | basis | value | n rtx-pro-6000-blackwell-96gb | qwen-qwen3-0-6b-gguf | reported | 956.4 tok/s | n=1 rtx-pro-6000-blackwell-96gb | unsloth-llama-3-2-1b-instruct-gguf | reported | 699.9 tok/s | n=1 rtx-pro-6000-blackwell-96gb | google-gemma-3-1b-it | reported | 664.3 tok/s | n=1 rtx-pro-6000-blackwell-96gb | google-diffusiongemma-26b-a4b-it | reported | 528.7 tok/s | n=1 rtx-pro-6000-blackwell-96gb | mmangkad-qwen3-6-35b-a3b-nvfp4 | reported | 506.2 tok/s | n=1 rtx-pro-6000-blackwell-96gb | nvidia-nvidia-nemotron-3-5-lightning-30b-a3b-nvfp4 | measured | 494.7 tok/s | n=4 rtx-pro-6000-blackwell-96gb | meta-llama-llama-3-2-3b-instruct | reported | 489.2 tok/s | n=1 rtx-pro-6000-blackwell-96gb | inclusionai-ling-3-0-tiny | reported | 369.1 tok/s | n=1 rtx-pro-6000-blackwell-96gb | nvidia-qwen3-6-35b-a3b-nvfp4 | measured | 330.3 tok/s | n=3 rtx-pro-6000-blackwell-96gb | radixark-qwen3-8-27b-nvfp4-bf16-lmhead | reported | 296 tok/s | n=1 rtx-pro-6000-blackwell-96gb | google-gemma-4-26b-a4b-it | reported | 276.7 tok/s | n=1 rtx-pro-6000-blackwell-96gb | moonshotai-kimi-linear-48b-a3b-instruct | reported | 267 tok/s | n=1 rtx-pro-6000-blackwell-96gb | moonshotai-kimi-linear-48b-a3b-instruct | reported | 256.3 tok/s | n=1 rtx-pro-6000-blackwell-96gb | qwen-qwen3-6-35b-a3b-fp8 | reported | 253.7 tok/s | n=1 rtx-pro-6000-blackwell-96gb | redhatai-deepseek-coder-v2-lite-instruct-fp8 | reported | 237.3 tok/s | n=1 rtx-pro-6000-blackwell-96gb | openai-gpt-oss-120b | measured | 196 tok/s | n=3 rtx-pro-6000-blackwell-96gb | qwen-qwen3-coder-next-fp8 | reported | 174.3 tok/s | n=1 rtx-pro-6000-blackwell-96gb | qwen-qwen3-5-9b | reported | 171.6 tok/s | n=1 rtx-pro-6000-blackwell-96gb | meta-models-muse-glimmer-30b-gguf | reported | 167.5 tok/s | n=2 rtx-pro-6000-blackwell-96gb | radixark-qwen3-8-flash-next-nvfp4 | reported | 161.2 tok/s | n=1 rtx-pro-6000-blackwell-96gb | nvidia-llama-3-1-8b-instruct-fp8 | reported | 158.1 tok/s | n=1 rtx-pro-6000-blackwell-96gb | preyazz-muse-glimmer-30b-nvfp4 | reported | 152.2 tok/s | n=1 rtx-pro-6000-blackwell-96gb | poolside-laguna-s-2-1-nvfp4 | reported | 149.6 tok/s | n=2 rtx-pro-6000-blackwell-96gb | unsloth-qwen3-6-27b-nvfp4 | reported | 138.6 tok/s | n=2 rtx-pro-6000-blackwell-96gb | moonshotai-kimi-linear-48b-a3b-instruct | measured | 119 tok/s | n=4 rtx-pro-6000-blackwell-96gb | sakamakismile-qwen3-6-27b-text-nvfp4-mtp | reported | 117.4 tok/s | n=2 rtx-pro-6000-blackwell-96gb | orcarouter-qwen3-8-27b-uncensored-fp8 | measured | 113.7 tok/s | n=3 rtx-pro-6000-blackwell-96gb | sakamakismile-qwen3-8-27b-mtp-nvfp4 | reported | 112.1 tok/s | n=1 rtx-pro-6000-blackwell-96gb | zai-org-glm-4-5-air | reported | 108.9 tok/s | n=1 rtx-pro-6000-blackwell-96gb | redhatai-muse-glimmer-30b-fp8-block | reported | 106.6 tok/s | n=1 rtx-pro-6000-blackwell-96gb | qwen-qwen3-6-27b | measured | 105.7 tok/s | n=6 rtx-pro-6000-blackwell-96gb | unsloth-qwen3-8-27b-gguf | measured | 100.7 tok/s | n=3 rtx-pro-6000-blackwell-96gb | qwen-qwen3-8-27b-fp8 | reported | 100.4 tok/s | n=2 rtx-pro-6000-blackwell-96gb | radixark-qwen3-8-27b-nvfp4 | reported | 97.4 tok/s | n=1 rtx-pro-6000-blackwell-96gb | cerebras-minimax-m2-5-reap-139b-a10b | measured | 97.2 tok/s | n=3 rtx-pro-6000-blackwell-96gb | qwen-qwen3-6-27b-fp8 | reported | 96.2 tok/s | n=1 rtx-pro-6000-blackwell-96gb | qwen-qwen3-6-27b-fp8 | measured | 92.6 tok/s | n=3 rtx-pro-6000-blackwell-96gb | nvidia-qwen3-14b-fp8 | reported | 90.8 tok/s | n=1 rtx-pro-6000-blackwell-96gb | unsloth-qwen3-8-27b-gguf | measured | 88.9 tok/s | n=4 rtx-pro-6000-blackwell-96gb | google-gemma-4-12b-it | reported | 86.9 tok/s | n=1 rtx-pro-6000-blackwell-96gb | qwen-qwen3-8-27b | reported | 84.5 tok/s | n=1 rtx-pro-6000-blackwell-96gb | qwen-qwen3-8-27b | measured | 81.8 tok/s | n=4 rtx-pro-6000-blackwell-96gb | deepseek-ai-deepseek-v4-flash | reported | 80.8 tok/s | n=1 rtx-pro-6000-blackwell-96gb | unsloth-qwen3-8-27b-gguf | measured | 79.3 tok/s | n=7 rtx-pro-6000-blackwell-96gb | aiconjured-qwen3-8-27b-uncensored-hauhaucs-aggressive-mtp-gguf-q8-nvfp4 | reported | 73.8 tok/s | n=2 rtx-pro-6000-blackwell-96gb | qwen-qwen3-6-27b | measured | 72.1 tok/s | n=6 rtx-pro-6000-blackwell-96gb | unsloth-qwen3-8-27b-gguf | measured | 67.8 tok/s | n=3 rtx-pro-6000-blackwell-96gb | qwen-qwen3-8-27b | reported | 64.7 tok/s | n=1 rtx-pro-6000-blackwell-96gb | unsloth-qwen3-8-27b-gguf | measured | 61 tok/s | n=3 rtx-pro-6000-blackwell-96gb | unsloth-qwen3-6-27b-mtp-gguf | reported | 60.1 tok/s | n=1 rtx-pro-6000-blackwell-96gb | unsloth-qwen3-8-27b-gguf | reported | 57.5 tok/s | n=2 rtx-pro-6000-blackwell-96gb | qwen-qwen3-6-27b | reported | 56.4 tok/s | n=1 rtx-pro-6000-blackwell-96gb | nvidia-qwen3-6-27b-nvfp4 | measured | 51.3 tok/s | n=9 rtx-pro-6000-blackwell-96gb | qwen-qwen2-5-coder-14b-instruct | reported | 50.3 tok/s | n=1 rtx-pro-6000-blackwell-96gb | unsloth-qwen3-8-27b-gguf | measured | 50.2 tok/s | n=3 rtx-pro-6000-blackwell-96gb | meta-models-muse-glimmer-30b | reported | 48.6 tok/s | n=2 rtx-pro-6000-blackwell-96gb | unsloth-muse-glimmer-30b-gguf | reported | 48.1 tok/s | n=2 rtx-pro-6000-blackwell-96gb | unsloth-qwen3-6-27b-mtp-gguf | reported | 40.3 tok/s | n=1 rtx-pro-6000-blackwell-96gb | google-gemma-4-31b-it | reported | 40 tok/s | n=1 rtx-pro-6000-blackwell-96gb | qwen-qwen3-coder-30b-a3b-instruct-fp8 | reported | 26.1 tok/s | n=1 Capture or correct a number: /console (signed, Ed25519).