A developer has successfully deployed a 28.9 million parameter language model on an ESP32 microcontroller, costing just $8. The implementation demonstrates practical AI inference on ultra-low-cost hardware.
The project, shared on GitHub as esp32-ai, shows that capable language models can run on severely resource-constrained devices. The ESP32 microcontroller, widely available and inexpensive, typically features 4MB of flash storage and limited RAM.
Running LLMs on microcontrollers addresses edge computing use cases where cloud connectivity is unavailable or undesirable. Inference happens locally without network latency or privacy concerns associated with cloud services.
The implementation generated 122 points and 27 comments on Hacker News, indicating significant interest from the developer community. This work follows broader trends in model optimization, including quantization and pruning techniques that reduce model size without sacrificing substantial performance.
The approach opens possibilities for embedding AI capabilities directly into IoT devices, industrial equipment, and embedded systems where computational power and cost are primary constraints.
Samsung opened a temporary foldable-themed pub in London following its Galaxy Z Fold 8 launch event. The promotional venue featured alcohol-free beer that failed to impress visitors.
JetZero is developing blended-wing body aircraft designed to reduce fuel consumption and emissions compared to conventional tube-and-wing designs. The company aims to make the technology viable for commercial aviation.
General Motors is supporting sodium ion battery technology for grid energy storage, positioning the chemistry as a viable alternative to lithium-ion systems for large-scale power applications.
Following a successful 13th flight test, SpaceX intends to attempt catching Starship with the launch pad tower on its next mission. The company is targeting the booster capture system as its next major milestone.