Decent LLMs can run on anything now: https://github.com/he-be/turbo-fieldfare

Kiwix is great, but I'd also like a language model to be able to deeply interrogate all of that information much faster than I can read.

Just arrange its harness so that its responses are grounded in the source material and require source citations for everything. Then read the citations to confirm it's not a hallucination.

I like this "both / and" approach. Restructure this project to have the LLM source from local Kiwix data you've selected to make available offline, rather than a source of data you're unfamiliar with. References point directly to your Kiwix library.