PrismML, an AI startup founded by Caltech researchers and advised by UC Berkeley’s Ion Stoica, has adapted its tiny language models for smart glasses running on Qualcomm’s Snapdragon chips. At Qualcomm’s Snapdragon Summit on Wednesday, the chipmaker demonstrated PrismML’s 1-bit Bonsai LLM running locally on glasses built on the Snapdragon AR1 Gen 1 Platform.
The model is a 2-billion-parameter version tuned for vision and language, letting wearers ask in real time about what they are looking at. PrismML says its approach shrinks larger models by about 4x while retaining nearly all of their performance on standard benchmarks.
The company’s broader goal is open-weight AI that runs on devices and uses existing computing power more efficiently, positioning that as an alternative to relying on proprietary AI labs’ privacy promises and growing compute demands. The Qualcomm release is a step toward that vision, but no smart glasses product running PrismML has been announced yet.