I imagine that for most "emergency" scenarios, it'll be a lot cheaper and more-robust to focus on dumber devices that store large amounts of normal reference material, as opposed to a system with the battery/CPU/memory/etc. to run an LLM.
If someone will need something like a medical flowchart for first-aid, it's probably better to generate it as an artifact in advance and then get it verified by an expert.
This is couched in prepper nonsense, but it's got LLM, WikiPedia, maps, etc. A bunch of genuinely useful stuff to keep on a USB stick or whatever: https://www.projectnomad.us/
But, the current model you really want for an emergency kit is Gemma 4 12B QAT 4-bit. At ~7GB on disk, it's small enough to run on a tablet or any modern computer, slowly if you don't have a GPU or modern Apple silicon, but exceedingly smart for its size, excellent vision capabilities, good tool user, surprisingly good reasoning.
They want to ask the iOS Foundation model (frontier on device intelligence for something small) for instance about emergency procedures and life-saving info. I wouldn’t trust that model with much at all though. More likely to find what you need from miniature survival guides.
99% of the model "work" (meaning the connection to your computer) is just spinning a spinner - something that makes me want to wrap it with a mosh shell so I can just keep moving from network to network.
I feel that would be handy in all sorts of situations when networks are down.
If someone will need something like a medical flowchart for first-aid, it's probably better to generate it as an artifact in advance and then get it verified by an expert.
But, the current model you really want for an emergency kit is Gemma 4 12B QAT 4-bit. At ~7GB on disk, it's small enough to run on a tablet or any modern computer, slowly if you don't have a GPU or modern Apple silicon, but exceedingly smart for its size, excellent vision capabilities, good tool user, surprisingly good reasoning.