Open WebUI is the nice chat interface for talking to AI models yourself — the thing that makes a local model feel like a product instead of a terminal window. I run it on my Pi 4. It works. It’s also the single biggest RAM hog on the box at around 800MB, which on 4GB is noticeable.
This is the same Pi from the watchdog post, and it’s no coincidence. A hefty web app at 800MB plus everything else the Pi runs, on 4GB total — that’s the setup that used to wedge the machine every few weeks. The earlyoom configuration I wrote about exists largely because of this thing.
Would I do it again? On a Pi 4, honestly, it’s marginal. Pages load, chats work, but you’re spending a fifth of your RAM on a UI. On a Pi 5 with 8GB it would be a non-issue. The Pi 4 copes if it’s mostly idle otherwise — but pair it with anything else hungry and you’ll want the watchdog setup from the first post.
The appeal is real, though: a proper chat interface, on your own hardware, with nothing leaving the LAN. That’s worth 800MB to me. Just know what you’re signing up for on 4GB.
As an Amazon Associate, Headless Diaries earns from qualifying purchases made through links on this page.