PrismML fait tenir un modèle 27B dans l’iPhone. Cette version conserve les faits vérifiés et replace le sujet dans une lecture produit, infrastructure et gouvernance.
Ce qui s’est passé
PrismML fait tenir un modèle 27B dans l’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
Pourquoi c’est important
Le signal plus large est on-device AI is about cloud cost, privacy and latency as much as model size.
À surveiller
Le prochain point de vérification est third-party reproduction on real iPhones and whether sustained inference matches the launch claim.
Sources：Sina Finance/Global Market Broadcast, PrismML site, GitHub, Hugging Face, The Information, AppleInsider, Techmeme, CocoLoop.