News for hackers. Stuff that matters.
Re:How to Run Llama 3 405B on Home Devices? Build AI Cluster by duffyjp on Monday July 29, 2024 @09:59AM (#41100502)
There's a bit of info on the project page. It's CPU only, which is why GPU and VRAM is never mentioned: https://github.com/b4rtaz/distributed-llama

I'm using an old x99 board for my desktop currently. If I swap out the i7 with a Xeon it can take up to 512GB of ram. That would be pricey, but I could do 256 and the Xeon for under $300 total. Still a lot for a toy, and I'm sure it would be super slow...

There are no comments on this comment yet.