双 3090 老工作站跑 DeepSeek V4.1 Flash：1M 上下文 25 tok/s

Runner @RRunner144原推发布于 2026.10.25

在 X 上打开原推

Back home, got DeepSeek-V4.1-Flash-1017 on a pair of 3090s in a 2014 DDR4 workstation doing 25 tok/s using 1M context. I can't stop laughing and I know Nikos is only going to make this thing faster. ISTA IQ2_XXS Quant using 1M context

这条是引用着另一条写的：x.com/rrunner144/status/2114016152351338909