PrismML coloca modelo 27B no iPhone. Esta versão preserva os fatos verificados e lê a notícia pelo ângulo de produto, infraestrutura e governança.
O que aconteceu
PrismML coloca modelo 27B no 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
Por que importa
O sinal mais amplo é on-device AI is about cloud cost, privacy and latency as much as model size.
O que observar
O próximo ponto de verificação é third-party reproduction on real iPhones and whether sustained inference matches the launch claim.
Fontes：Sina Finance/Global Market Broadcast, PrismML site, GitHub, Hugging Face, The Information, AppleInsider, Techmeme, CocoLoop.