Re:I'm making LLMs work on small and old devices
by dava96 on Thursday November 12, 2026 @11:47AM
(#50470258)
Out of interest, what have you been doing with them?
Re:I'm making LLMs work on small and old devices
by ForHackernews on Thursday November 12, 2026 @12:21PM
(#50470792)
Running a pihole, a WeeWx weather station, a NAS backup server, a wireguard VPN, Zot container registry.
Re:I'm making LLMs work on small and old devices
by NortySpock on Thursday November 12, 2026 @01:34PM
(#50471963)
Funny, I use that exact website to find passively cooled hardware to use as a server.
I did get Qwen3.5 0.8B working at 5 tokens per second on the iGPU of a Dell Wyse 7020. I mostly use it to complain to; I have not yet found an agentic task for it. But also the CPU does plenty of small services and terraria servers and such.
https://nortyspock.github.io/blog/running-a-language-model-o...
Not my site, but same idea: https://www.parkytowers.me.uk/thin/
All this old/obsolete gear is plenty capable when used with the right software.