bestmodel.run / model — Qwen3.6-27B (agent view) category chat · Qwen/Qwen3.6-27B · 146 runs in the model record answer: 43.7 tok/s (model median) Honesty ladder: measured > reported > extrapolated > formula > no data yet. Empty fields stay empty — never filled with an estimate. rig | quant | median result | basis | ttft | peak vram | max context Arc Pro B60 24GB ×2 | 8-bit | 9.5 tok/s | reported | ttft 1,135ms | vram - GB | ctx 4,096 Arc Pro B70 32GB | 4-bit | 43.5 tok/s | measured | ttft 1,156ms | vram 17.5 GB | ctx 131,072 Arc Pro B70 32GB | 5-bit | 26.6 tok/s | measured | ttft 311ms | vram - GB | ctx 204,800 Arc Pro B70 32GB ×2 | 4-bit | 40.5 tok/s | reported | ttft -ms | vram - GB | ctx 1,024 Arc Pro B70 32GB ×2 | 8-bit | 25.7 tok/s | reported | ttft -ms | vram - GB | ctx 512 Arc Pro B70 32GB ×3 | 4-bit | 44.2 tok/s | measured | ttft -ms | vram - GB | ctx 1,024 Arc Pro B70 32GB ×4 | 4-bit | 33.1 tok/s | reported | ttft -ms | vram - GB | ctx 1,024 Arc Pro B70 32GB ×4 | 8-bit | 43.7 tok/s | reported | ttft -ms | vram - GB | ctx 4,096 Arc Pro B70 32GB ×4 | 16-bit | 54.2 tok/s | reported | ttft 79ms | vram 17 GB | ctx 262,144 AMD Ryzen 7 7840HS | 4-bit | 3.5 tok/s | reported | ttft -ms | vram - GB | ctx 2,048 GB10 Grace Blackwell 128GB | 4-bit | 33.3 tok/s | measured | ttft 632ms | vram 117 GB | ctx 262,144 M1 Max 64GB | 8-bit | 11.3 tok/s | reported | ttft 3,973ms | vram - GB | ctx 787 M5 Max 128GB | 4-bit | 19 tok/s | reported | ttft 174ms | vram - GB | ctx 8,192 Multi-GPU 28GB ×2 | 4-bit | 21.9 tok/s | reported | ttft 155ms | vram - GB | ctx 4,096 Radeon 8060S Graphics 103GB | 4-bit | 88.3 tok/s | reported | ttft 337ms | vram 18 GB | ctx 4,096 Radeon 890M 32GB | 4-bit | 4.9 tok/s | reported | ttft -ms | vram - GB | ctx 4,096 Radeon AI Pro R9700 32GB | 4-bit | 278 tok/s | reported | ttft 103ms | vram 16.6 GB | ctx 2,048 Radeon AI Pro R9700 32GB ×3 | 4-bit | 213.7 tok/s | reported | ttft 63ms | vram 16 GB | ctx 4,096 Radeon AI Pro R9700 32GB ×3 | 8-bit | 17.8 tok/s | measured | ttft 768ms | vram 49.4 GB | ctx 262,144 Radeon AI Pro R9700 34GB | 4-bit | 254.8 tok/s | reported | ttft 111ms | vram 17.5 GB | ctx 4,096 Radeon AI Pro R9700 57GB | 4-bit | 3.6 tok/s | reported | ttft 7,848ms | vram - GB | ctx 2,048 Radeon RX 7900 XTX 24GB | 4-bit | 28.4 tok/s | measured | ttft 490ms | vram - GB | ctx 262,144 RTX 3060 12GB ×2 | 4-bit | 17.6 tok/s | reported | ttft -ms | vram 18.2 GB | ctx 128,000 RTX 3090 24GB | 4-bit | 26.2 tok/s | measured | ttft 1,374ms | vram 0 GB | ctx 131,072 RTX 3090 24GB ×2 | 4-bit | 46.7 tok/s | reported | ttft 125ms | vram - GB | ctx 2,048 RTX 3090 24GB ×2 | 6-bit | 22.7 tok/s | reported | ttft 2,101ms | vram - GB | ctx 2,048 RTX 3090 24GB ×2 | 8-bit | 40.9 tok/s | reported | ttft 2,101ms | vram - GB | ctx 2,048 RTX 3090 Ti 24GB | 4-bit | 140.3 tok/s | reported | ttft 710ms | vram 22 GB | ctx 1,024 RTX 4090 24GB | 4-bit | 44.2 tok/s | measured | ttft 335ms | vram - GB | ctx 131,072 RTX 5060 Ti 16GB | 4-bit | 46 tok/s | reported | ttft 453ms | vram - GB | ctx 2,048 RTX 5090 32GB | 3-bit | 73.5 tok/s | measured | ttft 36ms | vram 13.5 GB | ctx 8,192 RTX 5090 32GB | 4-bit | 70.1 tok/s | measured | ttft 37ms | vram 20 GB | ctx 243,040 RTX 5090 32GB | 8-bit | 20 tok/s | reported | ttft 200ms | vram 16 GB | ctx 2,048 RTX PRO 6000 Blackwell 96GB | 4-bit | 105.7 tok/s | measured | ttft 1,150ms | vram - GB | ctx 15,907 RTX PRO 6000 Blackwell 96GB | 8-bit | 72.1 tok/s | measured | ttft 1,203ms | vram - GB | ctx 15,907 RTX PRO 6000 Blackwell 96GB | 16-bit | 56.4 tok/s | reported | ttft 99ms | vram - GB | ctx 2,048 RTX PRO 6000 Blackwell 96GB ×2 | 16-bit | 99.6 tok/s | reported | ttft 58ms | vram - GB | ctx 2,048 RTX PRO 6000 Blackwell 96GB ×4 | 16-bit | 146.1 tok/s | reported | ttft 51ms | vram - GB | ctx 2,048 RX 7900 XT 20GB | 4-bit | 60.6 tok/s | reported | ttft 85ms | vram - GB | ctx 2,048 RX 7900 XTX 24GB | 4-bit | 118.2 tok/s | measured | ttft 126ms | vram 16.8 GB | ctx 16,384 Ryzen AI Max 395 128GB | 4-bit | 112 tok/s | reported | ttft 290ms | vram 16.8 GB | ctx 2,048 Ryzen AI Max 395 128GB | 8-bit | 16.7 tok/s | reported | ttft 1,926ms | vram - GB | ctx 787 Ryzen AI Max 395 64GB | 4-bit | 12.4 tok/s | measured | ttft 4,572ms | vram 17.1 GB | ctx 10,240 Ryzen AI Max 395 64GB | 8-bit | 7.7 tok/s | reported | ttft 4,059ms | vram 27.8 GB | ctx 8,192 Tesla P100 32GB ×2 | 4-bit | 47.4 tok/s | measured | ttft 176ms | vram - GB | ctx 2,048 Tesla P100-PCIE-16GB 16GB | 3-bit | 7.5 tok/s | reported | ttft -ms | vram - GB | ctx 2,048 Tesla P100-PCIE-16GB 16GB ×2 | 5-bit | 17.9 tok/s | reported | ttft -ms | vram - GB | ctx 2,048