iPhone에서 27B 모델을 구동하면 클라우드는 끝
PrismML이 iPhone에 탑재 가능한 3.9GB 추론 모델 Bonsai 27B를 출시했습니다. 베이스 Qwen 성능의 90%를 유지하면서 지연 시간 없는 로컬 에이전트 구동을 가능하게 합니다.
prismml, founded by caltech researchers, released bonsai 27b, a 27b-parameter model based on alibaba's qwen that compresses weights to just 1-2 bits to fit entirely on an iphone 17 pro max. the small variant uses 3.9gb of space and generates roughly 11 tokens per second, allegedly maintaining 90% of the original model's performance and near-perfect accuracy in math and coding tasks. ceo babak hassibi confirmed that apple and other companies are testing the technology for speed and power efficiency. this compression strategy allows complex multi-step agents to run locally without cloud latency or data exposure, potentially enabling a new class of always-on, privacy-first ai applications.