alt Hacker NewsYou can keep scaling down! I spent $2k on an old dual-socket xeon workstation with 768GB of RAM - I can run Deepseek-R1 at ~1-2 tokens/sec.
Replies
jacquesm • last Saturday at 10:44 AM
I did the same, then put in 14 3090's. It's a little bit power hungry but fairly impressive performance wise. The hardest parts are power distribution and riser cards but I found good solutions for both.
➕ show 2 replies
ternus • last Saturday at 12:45 AM
And if you get bored of that, you can flip the RAM for more than you spent on the whole system!
a012 • last Saturday at 1:15 AM
And heat the whole house in parallel
fatata123 • last Saturday at 5:55 AM
[dead]
Just keep going! 2TB of swap disk for 0.0000001 t/sec