You don’t have to be a full-on “prepper” to at least occasionally wonder what would happen if civilization collapsed. One thing you probably couldn’t do is go on the Internet and ask your favorite AI how to purify water, repel zombies, or treat a burn, all of which may be highly relevant depending on your situation. Now, with Survival LLM, you have a chance.

The  LLM is pretty much the stock chatbot, but it is trained on survival topics, and it runs locally. Naturally, you need the Internet to set it up, so you’d want to do that now before everything hits the fan. The training set uses medical references, survival manuals, FEMA and CDC documents, and nearly a million Wikipedia articles. It includes the survival references in a library and links to them when answering, too.

The installer is small, but it assesses your system and loads a model based on what you have. If you have less than 32 GB of RAM, you’ll get the IBM Granite 4.2 8B model, which was able to correctly answer 14 of 22 test questions. Other models do better, including the NVIDIA Nemotron 3.5 Super model, which got 21 correct, but requires at least 128 GB of memory.

Now, somehow you have to power your computer, but that’s a separate problem. At least there will be plenty of GPUs to scavenge from abandoned data centers. We’ve seen prepper digital libraries before. More than one, in fact.

Large language models (LLMs) output language, but they are commonly tasked with making a decision or classification of some kind instead of writing an essay or chat reply. An LLM will be provided with input, and asked to classify that content in some way: with a rating, yes/no answer, a best-fit categorization, and so forth. A recent new type of model by the name of Jev was released only weeks ago and it is extremely fast, ultra-cheap, and laser-focused on that decision-making role. It can’t write even a single sentence, but it can classify and categorize very, very quickly.

Jev works like this: it still accepts text input, but it outputs only floating-point numbers. Those numbers are the “answers” to user-specified yes/no type questions, lists of choices, and scoring-type requests. [Simon Willison] provides a concise summary of what Jev does, and what makes this new category of model so interesting.

To say that the idea has caught on would be a wild understatement. Folks are making their own decision-type models and experiments in a flurry. Kev and Nimble are two examples (Nimble was added as a supported model in Ollama just recently, and is small enough to run locally with relative ease.)

If this type of local AI model was the missing link you needed to get an idea working, don’t keep it to yourself! Tell us all about it on the tips line.