作者： Jakub Rusinowski · 最后更新： 2026年7月10日
PrismML just fit a full 27-billion-parameter multimodal model into 3.9 GB — small enough to run on an iPhone. Here's how the 1-bit and ternary builds work, how much intelligence survives the compression, how fast it actually runs, and which build you should use.
For the last two years, the rule for AI on a phone was simple: keep it small. Three billion parameters, maybe four. Anything bigger wouldn't fit in memory — and if it did, it crawled. A 27-billion-parameter model, the kind you'd normally run on a desktop with a discrete GPU, was firmly out of reach. On 14 July 2026, PrismML broke that rule. Bonsai 27B is a full 27B multimodal model compressed down to 3.9 GB — small enough to load and run on an iPhone. It is, as far as anyone can tell, the largest model of its class ever to run on a phone. Here's what PrismML actually built, how the trick works…