Lawyer’s $9,450 private AI server of 12 used Nvidia V100s now runs every DeepSeek V4.1 Flash expert at 4-bit NVFP4 — up

deepseek8.0

A lawyer built a $9,450 private AI server using 12 used Nvidia V100 GPUs that now runs every DeepSeek V4.1 Flash expert at 4-bit NVFP4, achieving up to 184 tokens per second on code. The setup also cuts long-document res

Read full story at deepseek →