PrismML把27B模型塞進iPhone. 本文保留已核驗事實，並以產品、基礎設施與治理脈絡重新整理。
發生了什麼
PrismML把27B模型塞進iPhone is the current news peg. The verified record centers on these points:
- PrismML says it compressed a 27B dense Qwen 3.6 model to under 4GB for local iPhone 17 Pro use
- the company says an open model will be released next Tuesday
- Bonsai work lists 1-bit and 1.58-bit compression with local CPU and device backends
- real tests must check latency, heat, KV cache memory and quality loss
為何重要
更大的產業訊號是 on-device AI is about cloud cost, privacy and latency as much as model size.
接下來看什麼
接下來要看的重點是 third-party reproduction on real iPhones and whether sustained inference matches the launch claim.
參考來源：Sina Finance/Global Market Broadcast, PrismML site, GitHub, Hugging Face, The Information, AppleInsider, Techmeme, CocoLoop.