PrismML and Qualcomm Collaboration
The AI Lab PrismML, founded by Caltech researchers and advised by UC Berkeley’s Ion Stoica, has created a version of its tiny language models for smart glasses running on Qualcomm’s Snapdragon chips.
At Qualcomm’s Snapdragon Summit, the chipmaker showcased PrismML’s 1-bit Bonsai LLM, which can be run locally on AI smart glasses built on the Snapdragon AR1 Gen 1 Platform.
On-Device Vision and Language Capabilities
PrismML shrinks larger models substantially while retaining almost all of their performance on standard benchmarks. The smart glasses version is a 2-billion-parameter model tuned for vision and language, enabling wearers to query what they are looking at in real time.
Open-Weight Edge AI Vision
Prism’s broader goal is open-weight AI that runs entirely on-device and makes efficient use of existing hardware computing power. The startup positions this approach as an alternative to relying on proprietary AI infrastructure.
Releasing a model optimized for Qualcomm silicon represents a step toward that vision, though specific commercial smart glasses running PrismML have not yet been announced.
