Welcome • User Guide
ToS • Privacy • Canary
Donate • Bugs • License

©2025 Poal.co

1.2K

Yeah... I am currently in the process of re-designing my homeLab to also have AI compute and to increase the amount of RAM per node while still trying to not make it dump insane amounts of heat or add a extra $300/mo to my power bill. Ill probably be posting a lot more to this sub in the near-ish future as I come up with things and maybe want to bounce ideas off others.

Archive: https://archive.today/s9H4l

From the post:

>After years of self-hosting on a VPS in a datacenter, I’ve decided to move my services at home. But instead of just porting services, I’m using this as an opportunity to migrate to a more flexible and robust set up. I will deploy services on a single mini pc. Since I need to be able to experiment and learn without disrupting my services, I will need to be able to spin up Virtual Machines (VMs). Let’s explore how I deployed Proxmox Virtual Environment on a safe host for my specific needs as a homelabber, and how I automated as much of it as possible. In a follow-up post we will explore how to spin-up and configure VMs in a reproducible way on that setup.

Yeah... I am currently in the process of re-designing my homeLab to also have AI compute and to increase the amount of RAM per node while still trying to not make it dump insane amounts of heat or add a extra $300/mo to my power bill. Ill probably be posting a lot more to this sub in the near-ish future as I come up with things and maybe want to bounce ideas off others. Archive: https://archive.today/s9H4l From the post: >>After years of self-hosting on a VPS in a datacenter, I’ve decided to move my services at home. But instead of just porting services, I’m using this as an opportunity to migrate to a more flexible and robust set up. I will deploy services on a single mini pc. Since I need to be able to experiment and learn without disrupting my services, I will need to be able to spin up Virtual Machines (VMs). Let’s explore how I deployed Proxmox Virtual Environment on a safe host for my specific needs as a homelabber, and how I automated as much of it as possible. In a follow-up post we will explore how to spin-up and configure VMs in a reproducible way on that setup.
[–] • 1 pt (edited )

The only "cloud" service I really pay for is some compute time for a Uptime-Kuma instance to monitor a couple of things. I don't want them running local because everything except my main site is local, and having a local service monitoring a local service isn't good, especially when spooktrim goes down.

It's something like $22 a year for the CPU time, and the host deploys the application for you and provides SSL.

[–] • 1 pt

I was on the path of building a dedicated PC to do local AI things, but when I looked at the cost of parts alone (not power or the hassle of setting it up), I found I could get better results with just buying a commercial service. What I had sunk into parts would cover like 5 years of AI subscription costs.

That calculus might be different now or in a few years when older AI hardware hits eBay. As of about a year ago it didn't make sense for me.

[–] • 1 pt

Yeah, As much as I want 100% local only there is a huge cost of entry and the hardware will already be out of date and slower. Now, if you are willing to have the model run slower it might not be such a big deal but I have also read that it screws with the accuracy based on how much you can have loaded at a time...

It is a huge trade off. Though, with how things tend to go with hardware I am willing to be in about a year we might be able to get some used hardware for "cheap" compared to what it would cost even if it's a power hog.