V4.1 Flash-1017 在三张 V100 32GB 上跑到约 70 tok/s

AJ @ItsmeAjayKV原推发布于 2026.10.23

在 X 上打开原推

Wow, this is DeepSeek-v4.1-flash-1017 running on 3 Tesla V100 32GB and DDR4 ram. ~ 70 tok/s decode ~ 446 tok/s prefill - 256k token window Project Maya has now improved a lot, @PeasantSmith even created a new quant Maya-XS to make this happen. I'm downloading weights now, will be testing how this will perform on my 24GB 3090 + 64GB RAM.

这条是引用着另一条写的：「763B 参数 V4.1 Flash 跑在 3 张 V100 32GB 上」