Hand-cranked AI chatbot runs entirely offline on a Raspberry Pi, challenging data center dominance

Hand-cranked AI box lets you get a workout while you wait for answers

Datacenters got you down? Worried that even the most innocuous questions will spin up AI models running in water-guzzling, energy-sucking, planet-destroying hyperscalers? You need CrankGPT. No, we're not talking about surrendering to AI psychosis: we're talking about a literal hand-cranked machine loaded with a voice agent that can respond to questions and even translate speech into other languages, provided someone keeps the power flowing. There's an onboard custom-built capacitor board to store some juice, mind you, but it only provides around 20 seconds of crank-free runtime before you've gotta keep crankin' to keep it alive. That, and it takes a bit of time to get it running - according to the documentation website, it's a 30-second process "from the moment you start cranking to the moment you're having a conversation with CrankGPT." According to the AI expert duo behind the device, computer scientist Katrin Tomanek and former Google Advanced Technology and Projects Group technical project lead Alex Kauffmann, CrankGPT still delivers impressive results despite the need to perform some hard physical labor for your tokens (though we'd argue some exercise for your AI might not be a bad thing). "Asking Claude to add two numbers for you is like swatting a fly with a wrecking ball," Kauffmann told The Register in an email. This tongue-in-cheek demonstration, Kauffmann said, may be a bit of light fun, but it's an exercise in demonstrating what his and Tomanek's AI company, Squeez, is all about: small, private specialized AI models that, in a pinch, might not even need very much energy or a connection to the web to operate. "Squeez produces customized, efficient, and private models that can run on small, inexpensive hardware to solve specific problems," Kauffmann explained, citing tasks like voice recognition for someone with a strong accent or speech impediment, or specially-trained, local AIs that are subject matter experts in topics like gardening or auto repair, but won't touch subjects outside their wheelhouse. Contrary to the flashy dot-com for CrankGPT the pair have set up, Kauffmann told me, Squeez has no plans to pursue spin cycle class-powered AI stacks for dev teams, though he said if anyone wants to foot the bill, he'd be happy to give it a shot. "Off-the-shelf bike generators are shockingly expensive and they're fussy to build," Kauffmann said. Still, "a good biker can maintain a steady 120W output, so a class of twenty could power a Blackwell." Speaking of wheelhouses, what's inside that box? If there's a tiny computer in a 3D-printed box with a crank attached, there's a good possibility it's going to be a Raspberry Pi, and that's the case here. CrankGPT's brain is built on a stock RPi 5 with 8 GB of RAM and a cooling fan HAT, and audio input and output are handled by a dedicated I/O HAT designed for voice assistants running RPis. Power comes from the aforementioned crank, which is actually an off-the-shelf 20W switchable voltage hand crank unit built for emergency USB device charging, and is stored in the custom capacitor unit the duo built. "The neatest part of the whole thing is that you can actually feel the inference," Kauffmann told us. "The amount of resistance the crank presents varies depending on the amount of work the board is doing, so when it's really working (generating words for instance), the crank becomes much harder to turn than when it's idling waiting for you to say something." As for software, the device is running the most stripped-down, bare bones instance of DietPi the pair could compile, which is able to boot into a functional userspace in about three seconds. The voice agent is the truly original piece of work done for the project, as detailed in the documentation page, and was built entirely from scratch. "We wanted to understand the system end to end and have as few dependencies as possible," the documentation page notes. It's available on GitHub for those interested in trying it out. Speech recognition is handled by the Moonshine automatic speech recognition engine, chosen for its speed, while text-to-speech synthesis is handled by Piper, chosen again for its low-resource edge inference capabilities. As for the models running on the thinking itself, there are a few that are behind CrankGPT, with Liquid LFM2 1.2B providing a general-purpose voice agent, and Gemma 3 1B being used for translation. CrankGPT can switch between translation and various prompts (e.g., general question answering and games like two truths and a lie) via a knob on the side of the enclosure. "It's entirely configurable," Kauffmann told us. "We added a couple of physical inputs (the knob, a button, a switch) to make experimentation easier." Kauffmann added that he and Tomanek were surprised by how well the translation function worked. "We did no fine tuning, it's just a two-line prompt and it works really well for high-coverage languages," he explained. While the demonstration focuses on audio prompts and responses, Kauffmann explained that the device supports all sorts of different models, with the only real limitation being inference time and the amount of hand cranking one wants to do to get their response. "We've generated images (small), made poetry (bad), and written code using the same setup," the CrankGPT makers wrote in their documentation, all with "a hand crank, a little computer, and a small stack of speech and language models running locally." If you're interested in building your own CrankGPT model, keep an eye on the documentation page we linked earlier in this story, as Kauffmann told us he and Tomanek are planning to release all the plans and schematics in the coming days, while the aforementioned custom voice agent is already available for tinkering. "It's a pretty straightforward setup, the only tricky part is that SBCs like the Raspberry Pi will sometimes draw enough current to trigger a little generator's overcurrent protection," Kauffmann told us. If you have a spare $300 lying around (that's what Kauffmann estimates the RAM pricing surge has driven the build cost up to, from the $150 he spent when building CrankGPT last year), then you, too, may soon be able to build your own completely off-grid, standalone AI box so you can keep chatting with your favorite micro LLM if and when its bigger cousins knock the grid offline. ®

CrankGPT Is a Hand-Powered Chatbot to Guide You Through the Post-Apocalypse

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! 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, whose website 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, 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 variants (e.g., 350M or 1.2B), along with Gemma 3 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. 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.

CrankGPT is a hand-powered, fully offline AI bot powered by a Raspberry Pi and 8GB of RAM -- and I'm all for apocalypse-ready chatbots that don't need data centers

* An innovative new AI bot runs on manual crank power * It uses a Raspberry Pi and local AI models * The bot is built to work offline without an extra power source Making use of AI bots typically involves relying on cloud access and data centers, and giving up your information (and your chats) to one of the big tech companies. However, a new DIY gadget called CrankGPT works very differently. Built by the enterprising folks at Squeez Labs, the CrankGPT box (via Boing Boing) is powered by a hand crank. It runs on a Raspberry Pi with 8GB of RAM, and uses small, local AI models from Meta and Google to transcribe speech and run queries. As the demo video shows, if you find yourself in a post-apocalyptic world without electricity and internet connectivity, you can still get facts about hummingbirds and translate between languages through the power of your arm muscles. "Provided the electronics are kept dry and at a reasonable temperature, there's no reason this thing won't still work in a hundred years, though you'll definitely need a fresh SD card," explain the inventors in their rundown of how CrankGPT was made. Several plans available The makers of this clever box have even made a tongue-in-cheek landing page offering the CrankGPT for sale. If your AI needs are more demanding then you can upgrade to a system based on an exercise bike, or an entire gym of people pedaling. There's a more serious point here too though: Squeeze Labs is working on making AI smaller, cheaper, and faster so it can be run on more devices with no cloud connectivity required. That's better for user privacy and for the environment. AI companies are investing huge amounts in data center expansion in an attempt to keep up with the growing compute needs of coders and other users, and that means increasing demands on electricity supply and water usage. As Apple recently demonstrated with Siri AI, the most advanced and complex AI prompts need to be run on online servers. As models become more efficient over time and devices become more powerful, that should start to change. Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.

There's one AI machine that doesn't need a nuclear power station to run, and it points to a potential way forward in the memory crisis

AI is ruining everything, right? The economy, air quality, and computing as a whole have all felt the impact of the exponential growth in data centers for machine learning. However, there's one little hardware AI project that proves bigger isn't always better, and even shows a possible way out of the current memory crisis. It's called CrankGPT by Squeez Labs (via Hackaday) and the gist of it is simple: Have a little microcomputer run a tiny local model for AI voice assistance, then stick it in a box and power the whole thing with a hand crank. No massive power station, no endless racks of GPUs, no DRAM-destroying demands. The computer in question is powered by a standard 8 GB Raspberry Pi and pretty much nothing else. It handles the voice recognition node, the local LLM (large language model), and the text-to-speech stuff. CrankGPT's creators built their own edge voice agent to process the complete algorithm (i.e. voice input > LLM stage > text-to-voice output). There's a brief demo of CrankGPT in action at the bottom of the webpage for the project, and it seems to work pretty well. Of course, there are strict limitations as to what it can do, as the Raspberry Pi 5 isn't exactly designed to be an inference powerhouse. It also takes roughly 30 seconds of cranking for the system to boot and be ready for any input, too. What interests me most about CrankGPT is the fact that, as a proof of concept, it shows that edge AI has a clear future ahead of it. Being entirely offline and with a local LLM, it's unmatched for privacy, but I reckon there's something more significant here. The hardware required for this is extremely light: just a little processor, 8 GB of LPDDR4X, and a small SD card to host the OS and required data. Video credit: Squeez Labs AI training is always going to be done via hulking data centers, but ChatGPT shows that you don't need the same for small-scale inference. If a hand-powered box can do it, then so can a basic laptop, phone, or even a watch. This hardware already exists on a vast scale across the world; all that's needed are the right AI models and agents to make it all work as intended. Should inference truly head off in that direction, it could significantly lessen the rampant demand for the kind of DRAM and NAND flash used in massive AI machines, and thus help bring an end to the current memory crisis. With hundreds of billions of dollars invested in AI training and inference, though, there's not much impetus for the industry to scale things right back and target the hardware that we already have. But wholesale change rarely happens overnight; all that's needed is for someone to show the way forward, and that's what CrankGPT has done.