Looking for Dual GPU Tips and tricks.
英文标题:Looking for Dual GPU Tips and tricks.
Just added a second 5060 16gb to my server for 32gb total VRAM + 80GB of ECC DDR4 It's pcie 3.0 so I think tensor parallel is not going to run well in any config but I get around 3200 tok/s prompt processing and 100 tok/s generation with qwen 3.6 35B. 27b runs at about 600 PP / 23 generation i
打开原文相关 2 · 机会 0
中文
Just added a second 5060 16gb to my server for 32gb total VRAM + 80GB of ECC DDR4 It's pcie 3.0 so I think tensor parallel is not going to run well in any config but I get around 3200 tok/s prompt processing and 100 tok/s generation with qwen 3.6 35B. 27b runs at about 600 PP / 23 generation i
中文全文翻译正在补齐,可先查看下方英文原文。
English / 原文
Just added a second 5060 16gb to my server for 32gb total VRAM + 80GB of ECC DDR4 It's pcie 3.0 so I think tensor parallel is not going to run well in any config but I get around 3200 tok/s prompt processing and 100 tok/s generation with qwen 3.6 35B. 27b runs at about 600 PP / 23 generation i