Many LLM operations rely on fast memory and gpus seem to have that. Even though their memory is soldered and vbios is practically a black box that is tightly controlled. Nothing on a GPU is modular or repairable without soldering skills(and tools).
I think the biggest limiting factor for your mini PC will always be the VRAM and any workload that enjoys that fast RAM speed. Really, I think this mini PC from framework is only sensible for certain workloads. It was poised as a mobile chip and certainly is majorly power efficient. On the other hand I don’t think it is for large scaling but more for testing at home or working at home on the cheap. It isn’t something I expected from framework though as I expected them to maintain modularity and the only modularity here is the little USB cards and the 3D printed front panel designs lol
Edit
Personally I am in that niche market of high RAM speed. Also, access to high VRAM for occasional LLM testing. Though it is an AMD and I don’t know if am comfortable switching from Nvidia for that workload just yet. Renting a GPU is just barely cheap enough.
Bored sexy look is really interesting, I like it. I also love the pigtails
I run a personal dnsmasq just for dns resolving/routing. It integrates well with Networkmanager. Easy to work with and very reliable to have the DNS resolution and routing be handled by dnsmasq. Single command to reload NetworkManager which also reloads the integrated dnsmasq. I like it and it offers a lot of control for me. I hate having to use the hosts file for when I am connecting to labs via VPN with their own network. dnsmasq is way better at handling subdomains than the hosts file and it feels way more reliable than just hoping the minimal DNS routing system works properly.