Ollama and all that runs on it its just the firewall rules and opening it up to my network that’s the issue.

I cannot get ufw, iptables, or anything like that running on it. So I usually just ssh into the PC and do a CLI only interaction. Which is mostly fine.

I want to use OpenWebUI so I can feed it notes and books as context, but I need the API which isn’t open on my network.

I was thinking about that now that I have Mac Minis on the mind. I might even just set a mac mini on top next to the modem.

Ollama + Gemma/Deepseek is a great start. I have only ran AI on my AMD 6600XT and that wasn’t great and everything that I know is that AMD is fine for gaming AI tasks these days and not really LLM or Gen AI tasks.

A RTX 3060 12gb is the easiest and best self hosted option in my opinion. New for <$300 and used even less. However, I was running with a Geforce 1660 ti for a while and thats <$100

A mac is a very funny and objectively correct option

I think I’m going to have a harder time fitting a threadripper in my 10 inch rack than I am getting any GPU in there.

I do already have a NAS. It’s in another box in my office.

I was considering replacing the PIs with a BOD and passing that through to one of my boxes via USB and virtualizing something. I compromised by putting 2tb Sata SSDs in each box to use for database stuff and then backing that up to the spinning rust in the other room.

How do I do that? Good question. I take suggestions.

With a RTX 3060 12gb, I have been perfectly happy with the quality and speed of the responses. It’s much slower than my 5060ti which I think is the sweet spot for text based LLM tasks. A larger context window provided by more vram or a web based AI is cool and useful, but I haven’t found the need to do that yet in my use case.

As you may have guessed, I can’t fit a 3060 in this rack. That’s in a different server that houses my NAS. I have done AI on my 2018 Epyc server CPU and its just not usable. Even with 109gb of ram, not usable. Even clustered, I wouldn’t try running anything on these machines. They are for docker containers and minecraft servers. Jeff Geerling probably has a video on trying to run an AI on a bunch of Raspberry Pis. I just saw his video using Ryzen AI Strix boards and that was ass compared to my 3060.

But to my use case, I am just asking AI to generate simple scripts based on manuals I feed it or some sort of writing task. I either get it to take my notes on a topic and make an outline that makes sense and I fill it in or I feed it finished writings and ask for grammatical or tone fixes. Thats fucking it and it boggles my mind that anyone is doing anything more intensive then that. I am not training anything and 12gb VRAM is plenty if I wanna feed like 10-100 pages of context. Would it be better with a 4090? Probably, but for my uses I haven’t noticed a difference in quality between my local LLM and the web based stuff.

That’s fair and justified. I have the label maker right now in my hands. I can fix this at any moment and yet I choose not to.

I’m man feeding orphans to the orphan crushing machine. I can stop this at any moment.

Oh and my home office set up uses Tiny in One monitors so I configured these by plugging them into my monitor which was sick.

I’m a huge fan of this all in one idea that is upgradable.

These are M715q Thinkcentres with a Ryzen Pro 5 2400GE

Not really a lot of thought went into rack choice. I wanted something smaller and more powerful than my several optiplexs I had.

I also decided I didn’t want storage to happen here anymore because I am stupid and only knew how to pass through disks for Truenas. So I had 4 truenas servers on my network and I hated it.

This was just what I wanted at a price I was good with at Like $120. There’s a 3D printable version but I wasn’t interested in that. I do want to 3D print racks and I want to make my own custom ones for the Pis to save space.

But this set up is way cheaper if you have a printer and some patience.

Not much. As much as I like LLMs, I don’t trust them for more than rubber duck duty.

Eventually I want to have a Copilot at Home set up where I can feed a notes database and whatever manuals and books I’ve read so it can draw from that when I ask it questions.

The problem is my best GPU is my gaming GPU a 5060ti and its in a Bazzite gaming PC so its hard to get the AI out of it because of Bazzite’s “No I won’t let you break your computer” philosophy, which is why I did it. And my second best GPU is a 3060 12GB which is really good, but if I made a dedicated AI server, I’d want it to be better than my current server.

I just built a mini rack with 3 Thinkcentre tiny PCs I bought for $175 (USD) on eBay. All work great.

That’s what I was thinking too. Ijust feel better having another layer between the open web an my server

True but I’m wanting to run VMs for specific tasks as well (mostly game servers) and I like to virtualize Linux distros I wanna play with as well as keep a running windows VM for the off chance I need windows ever.

Apartment is too small and my partner is too noise sensitive to get away with a rack. So my localLLM and Jellyfin encoder plus my NAS exists like this this summer. Temps have been very good once the panels came off.

Ansible is next on my list of things to learn.

I don’t think I’ll need to dedicate all of my compute space to K8s probably just half for now.

The rats nest is behind it

I need to re do some of the wiring.

I have all 4 power cables braided and zip tied together with the single data cable so its nice to pull out and put back into the entertainment center.

Only problem is I only had four 1 foot Ethernet cables and three 7 foot cables. So I used the 1 footers for the Pis and the 7 footers are bundled up as best I could and neatly hidden.

I’m waiting on some color coordinated .5 foot cables from Cables and Kits and I will swap the switch and patch panel. I want the Pis to have that one cable and that’s it, but I also want all the patch panel ports to work.

Rack shown

This is a 52pi 10 inch rack 8U

I have 4 raspberry Pi4’s 4gb running with POE

Some TP-link gigabit switch with 4/poe ports

3 Thinkcentre Tiny with a ryzen 5 2400GE 32 gigs ddr4 RAM, 512 Sabrent PCIE Gem 4 NVME boot/VM drive, 512 PNY Sata SSDs for databases

I have a bigger server for AI stuff and storage. This is just Tue “production” server for my websites and Git repos

I stole the set up idea from my man Jan Wildeboer

https://jan.wildeboer.net/2025/05/Cute-Homelab/