Keith(@gnukeith):I don't think people realize just how much of an engineering marble DeepSeek V4.1 Flash is, because guess how much RAM you need for 1M context window? For reference Llama 3.3 70B would need around 320gb of RAM. Qwen 3 8B around 144gb of RAM. DSV4.1F? Less than 0.9gb.

Keith

@gnukeith

Professional larper @Brave @Obscuravpn

Joined May 2023

367 Following 21.8K Followers

Keith@gnukeith

2026.10.29 01:20

I don't think people realize just how much of an engineering marble DeepSeek V4.1 Flash is, because guess how much RAM you need for 1M context window? For reference Llama 3.3 70B would need around 320gb of RAM. Qwen 3 8B around 144gb of RAM. DSV4.1F? Less than 0.9gb.

114

244

Forward to community

Most Popular Users