I am interested in this in general too. I have a 3090 which I know isn't much but have been thinking of trying to get a second 3090 and using an NVLink to increase to 48Gb. Mostly for learning and testing purposes, and then to eventually offer to donate to my wife's local school district a local model they own (since teachers aren't supposed to put student info online, that includes private LLM models like ChatGPT, but they keep accidentally doing so anyway).

But one project at a time, and setting up this LLM would help my two friends if they have issues (it's easy to forget for people like us that to nearly everyone else, setting up Jellyfin properly with remote access as well as things like Docker are not easy, even when they have base level knowledge), but it might help others in the future too that might then get interested in self hosting. A 24/7 guide can make a difference I think in someone actually trying self hosting or not.