# CrankGPT Is a Hand-Powered Chatbot to Guide You Through the Post-Apocalypse > Source: > Published: 2026-06-18 14:10:30+00:00 The apocalypse will be a pain in the ass for any number of possible reasons. The giant robot dinosaurs! The constant 1950s music blaring from mysteriously functional radios! The possibility of ending up as livestock in a terrifying cannibal basement and wondering why you didn’t read *The Road* more closely. But clearly, the absolute *worst* part of it will be not having ChatGPT to tell you what to do anymore. How is one to live without a weird internet parrot whispering sweet nothings in one’s ear all day long?? Well, never fear, because one plucky inventor has already foreseen the disaster that an LLM-less post-apocalypse would present, and they’ve planned for exactly that eventuality. Behold: [CrankGPT](https://crankgpt.com/)! From the name, you might think that this is just ChatGPT with a built-in suite of antivaxx prompts, but no! This is an LLM for a grid-less future: a self-contained, battery-less box that uses an old-style hand crank for power. The box contains a Raspberry Pi 5 with 8GB of RAM, an audio input/output card, and a 20W hand-cranked generator. CrankGPT is the work of the two-person company [SqueezLabs](https://squeezlabs.com/), whose [website](https://squeezlabs.com/) describes its remit as “making AI smaller, cheaper, and faster so you can run it anywhere.” Oh happy day! According to the device’s [website](https://squeezlabs.github.io/handcrank/), the generator connects to a capacitor board that the duo designed themselves; the board ensures that the voltage supplied to the Raspberry Pi remains steady. One interesting wrinkle is that “you can feel [the power load] through the crank: when LLM inference and speech synthesis run together, the crank gets a lot harder to turn.” The LLM itself can be one of several alternatives: SqueezLabs recommends “small [Liquid AI LFM2](https://www.liquid.ai/blog/liquid-foundation-models-v2-our-second-series-of-generative-ai-models) variants (e.g., 350M or 1.2B), along with [Gemma 3](https://gizmodo.com/google-launches-gemini-3-pro-to-usher-in-a-new-era-of-intelligence-2000687550) in its 1B form.” The machine takes voice input through its audio card, converts the speech to text via a custom voice agent written by the designers, and then outputs the LLM’s response into text-to-speech software [Piper](https://github.com/OHF-Voice/piper1-gpl). In all seriousness, this is an interesting proof of concept for running demanding software on a relatively small energy budget, and also a demonstration that LLMs don’t *have* to hoover up vast amounts of power to function. As the designers explain, “It offended our European small-practical-car sensibilities to see people around us throwing kilowatts and thousands of tokens at tasks small models could accomplish just as well as huge ones, for a fraction of the cost and energy.” Unfortunately, with Silicon Valley at the wheel, it doesn’t look like the supersize-me philosophy that characterizes LLM development at the moment is going anywhere anytime soon. But when the bombs fall, it’ll be the small-practical-car types who have the last laugh. Well, until the neck-wider-than-head crew arrives with their AR-15s, anyway. ChatGPT, what’s for dinner? … Me, you say? Oh.