PrismML brings its tiny LLMs to Qualcomm-powered smart glasses

PrismML is adapting its small language models to run on smart glasses powered by Qualcomm chips. The company’s broader goal is open-weight AI that operates directly on devices and uses their existing compute more efficiently.

The move reflects a growing push toward on-device AI for wearables, where latency, privacy, and power efficiency matter. If tiny models become capable enough, smart glasses could rely less on cloud services and support more responsive ambient computing experiences.