PrismML puts 2B-parameter LLM on Qualcomm smart glasses
prismml releases 2-billion-parameter llm for qualcomm-powered smart glasses, enabling real-time vision and language queries locally on device.
prismml, founded by caltech researchers and advised by uc berkeley's ion stoica, has developed a version of its tiny language models for smart glasses powered by qualcomm's snapdragon ar1 gen 1 platform. the model, called 1-bit bonsai llm, has 2 billion parameters and is designed for vision and language tasks. it can run locally on the device, enabling wearers to ask questions about their surroundings in real time. prismml's goal is to enable open-weight ai that runs on devices, making better use of their computing power. releasing a model for qualcomm's chip is a step toward that vision.