انضم إلى نوستر
2026-07-22 08:18:10 CEST
in reply to

npub1rr…dpfl2 on Nostr: npub1y6ckp…xjkf0 > What do you expect to get out of local AI? I don't. I was ...

> What do you expect to get out of local AI?

I don't. I was shocked that anything ran on my machine at all, since it only has Intel onboard graphics. I was just curious enough to try it and see if it worked.

I mean we're only talking 3-10 tokens/sec, so it's not like it's remotely fast, but I found it at least usable.

The machine Rob Braxman recommends is this one:

https://www.amazon.com/Beelink-126TOPS-LPDDR5X-PCIe4-0...

> Basic image,music, and chat can do great on 12-16GB GPU

I'd expect less than that for images if the Ollama ever gets the flux2-klein model working on Linux. I haven't even look at music generation though.