Ollama is a big thing, do you want it to be fast? You will need a GPU, how large is the model you will be running be? 7/8B with CPU not as fast but no problem. 13B slow with CPU but possible

I would take that any day!

That is true, I mean I mostly only use my homelab except some game servers that I am running. And you are totally right. Only reason why I want to run proxmox or in general why I have a homelab is to learn more about servers and self hosting. I am currently in the first year of my apprenticeship and I have learned so much since I got my server up and running 😄 and I think I can learn a lot more when I am using proxmox

Please keep me up to date what you try and how you are trying to migrate it over! :D and obviously good luck

I am in the same boat currently and thinking about how I can migrate my stuff over without having a 1 month downtime EDIT: after reading all the comments I’m still not sure if I should do it or like I said even how. I love my unraid it fits me well however I think I also have fallen in love with proxmox

I don’t think it matters too much but I’m not sure, I just sticked to using the dedicated extension and it’s working good

Meh that sucks i even have a perfectly working ddns, I mean I know I don’t get something like a PTR record but i wish that mail hosters would allow for more self hosting options

That’s a good idea. When I’m gonna look should I scout for new ones or can I look for already used once? Also how many should I buy 2 for a raid 1 or 3 or something to use a raid 5/10

Appreciate it 😂 love it already

Appreciate the offer. I recently only build my home server and I just started to selfhost things Although I am looking on what to expand and when I dont think I will buy Hard drives or something else in the next 2 months for my server

Yeah I think I remember thank you 😅 I just noticed are these also valid options for Germany or should I go with my usual places to hard drives of? Anyway thank you for your comment :)

Oh fuck yeah I should have said that I live in Germany… Thank you for your comment

Well yeah that approach would work if you train it on one model but that doesn’t mean it would work on another model, but for the normal user who uses chatgpt it is probably enough to detect it at least 80-90% of the times

Thank you for the resource that’s really unfortunate to read. Are there any major differences between gitea bad forgejo? If not I will probably go with forgejo then

Can you elaborate on what questionable things they did? I am thinking of hosting my own gitea instance