Caltech spinout PrismML released Bonsai 8B, a 1-bit large language model that compresses AI into just 1.15 GB of memory—14 times smaller than full-precision counterparts—while running 8 times faster and using 5 times less energy on edge hardware. Founded by Caltech professor Babak Hassibi, PrismML's architecture represents weights as simple signs {-1, +1} with shared scale factors, achieving an intelligence density score of 1.06/GB compared to 0.10/GB for competing model Qwen3 8B, though Qwen3 still leads on traditional benchmarks. The model runs natively on Apple devices and Nvidia GPUs, with PrismML positioning the technology to enable on-device AI agents, real-time robotics, and secure enterprise systems without cloud dependency.
Nov 12, 2026 · 2 sources
Nov 12, 2026 · 3 sources
Nov 12, 2026 · 2 sources
Nov 11, 2026 · 3 sources
Story comments
Loading comments…