I’ve been thinking about adding this to my “Fuck it, I’ll do it myself” / SHTF pile. I have a spare 10-15GB for a good selection of basic articles (across sciences, history, pop culture trivia etc).
https://get.kiwix.org/en/solutions/hotspots/content-bundles/
https://get.kiwix.org/en/solutions/hotspots/imager-service/
There’s something inherently cool about having wikipedia in a box (yes, you’d likely need to refresh it once a year) but I’ve never heard of anyone actually self hosting a Kiwix instance.
You must log in or # to comment.
Acronyms, initialisms, abbreviations, contractions, and other phrases which expand to something larger, that I’ve seen in this thread:
Fewer Letters More Letters AP WiFi Access Point NAS Network-Attached Storage VPN Virtual Private Network
3 acronyms in this thread; the most compressed thread commented on today has 3 acronyms.
[Thread #261 for this comm, first seen 29th Apr 2026, 12:00] [FAQ] [Full list] [Contact] [Source code]
Yes, and I actually use it to train a local llm so I’m not hammering the internet. I have a ton of storage, and like to keep my kids in the sandbox, so we have wikipedia, project gutenberg, kahn academy, and a bunch of others all hosted behind an apache reverse proxy which is using mellon so there’s LDAP auth.
Do you actually train the LLM or use RAG? I have been looking for a local LLM + Wikipedia RAG solution for a while now.
For now I just have kiwix-serve + searxng doing a simple search but the Kiwix search is…questionable.
Somewhere in my documents, I have a scoped ticket for how to use kiwix as the source for the LLM to pull information directly from, populate its answer organically, and naturally respond to question at hand, without word-vomiting a wiki entry complete. The last I looked, you can poll the kiwix DB directly without using the search engine.
I can dig that up for you if it still exists; it’s actually why I’m looking at kiwix (back burner project for now but the spirit moved me).
PS: You’re aware of LLM-wiki? That might suit your purposes better, if your corpus is bespoke and updating. Works nicely.
That was actually my immediate thought. I already have Wikipedia as a trusted source for llm, but I would prefer to self host and not hammer them.
130GB to fit the entirely of Wikipedia is basically nothing and I’m mildly embarrassed not to have done it already.
I also try to participate in some of the farms, running zimit and mwoffliner to help make more archives. Feels like I’m helping.
Yep, and I love it.
I’ve got a little Banana Pi M4 Zero (PiZero form factor but much more powerful and with 4 GB RAM) loaded up with, among other useful tools, Kiwix and the full Wikipedia dump. I just refreshed it with the 2026-02 full dump, so I’m caught up for the year. I’ve also got a lot of other offline docs loaded up (React, Bun, and the devdocs for several libraries I use) and it’s nice to have local copies of those instead of googling every time.
Surprisingly, the full ~130 GB Wikipedia dump works fine on a regular Pi Zero 2 with 512 MB RAM. I don’t know how ZIM works but it does work very very well.
Similar setup here. Orangepi zero that starts kiwix server at boot and switches the wifi to AP mode. Just plug it in, connect to kiwix WiFi, access kiwix.local via phone browser, and shazam.
Nice! Those AllWinner boards are a little tricky to get going and have some quirks, but the price is great for the extra horsepower you get. Granted, I use the latest Armbian since the manufacturer’s images are all quite old.
I actually have a spare pi4 doing nothing, so was thinking of adding this to its jobs list.
130GB for the entire thing? And the pi doesn’t choke on indexing / searching it?
On that: how capable is the search engine (I assume it has one?)
130GB for the entire thing? And the pi doesn’t choke on indexing / searching it?
That was my thought. I knew it couldn’t hold it in RAM but thought it would be doing crazy IO and limited by being on SD, but it seems to not be a problem. Like I said, I don’t know how ZIM does it, but it does it well. Must have some kind of index that lets it fast travel to the correct blocks or something. I dunno lol.
how capable is the search engine (I assume it has one?)
Yep, it has search. It’s…okay but kind of primitive. It’s not slow, and if you’re searching for something that’s fairly unique (as far as keywords go), it does well. But if you’re searching something like an acronym where it shows up as a regular word in other entries, it’s a lot more hit or miss.
I got Kiwix at home and on my iPhone it rocks.
I do on my TrueNAS in a docker container. I have about 1TB of zim files hosted including pre-LLM copies of German, English and French Wikipedia as well as the last two current versions in these languages.
Aditionally I have project Gutenberg Books in german and english as well as lots of random technical, medical, survival, etc stuff that I came accross - a lot of that is trash though, but sorting is too time consuming and my NAS has 48TB so who cares…
Humorously, you could use an agent to help you sort things. If theres anything it’s good at, it’s sorting.
How do you like TrueNAS? I’m too locked in to Synology at this point—with almost 800tb (in physical drives, less actual because of redundancy), and several devices.
Pretty happy woth TrueNAS, actually came from Synology and bought a UGreen DXP4800Plus, didn’t like the UGOS on it and pretty much immediately switched tp TrueNAS. It’s been absolutely flawless for about 15 months by now, docker integration in the OS is a bit limited by I run my compose stacks managed through dockge anyways.
I won’t let LLMs crawl my data, it’s mine and mine alone :)
That’s awesome. If I understand correctly, kiwix server creates a local site you can access from anything on your wLAN, as a transparent website? I take it it auto populates with your ZIM files, and that you can add to it (eg: project Gutenberg).
If so, that’s a hell of a thing.
Yep exactly. Also you can have other people (friends/family) have access via VPN, Tailscale, etc.
Yes. This is my ansible role that deploys it
Yes, I self host the English Wikipedia dump, as well as a few cooking sites and topic specific stack exchange dumps available in zim format.
My goal is:
- reduce dependence on public internet. In the event of an outage or restriction I’d like some books and other content I can use to entertain myself
- locally preserve a snapshot of information before it is possibly diluted by LLM edits
Yes, it’s helpful
Yup! Here’s my setup:
https://github.com/shadybraden/compose/blob/main/kiwix/compose.yaml
I switched to an N150 some time ago, but I previously had it running perfectly on a Pi 4 with only 2GB of RAM. There’s actually a lot more content available than just Wikipedia! You can even archive your own websites using https://zimit.kiwix.org/
It’s fun and Kiwix is impressively lightweight, it uses less than 50 MB of RAM, even with an article loaded.
Is there an actual download link? They want $20 for the Raspberry Pi image
Damn their website has become a mess. Anyway
