Unverified50% confidenceFactExact time
苹果采用模型路由架构，简单查询由本地模型处理，复杂任务转发给云端GPT-4o
1
Sources
50%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
UnverifiedAt WWDC 2023, Apple announced its Apple Intelligence strategy, deeply embedding OpenAI's ChatGPT into Siri using a model routing architecture (simple queries handled locally, complex tasks forwarded to cloud-based GPT-4o).80% similarUnverifiedApple Intelligence relies on Apple's self-developed Neural Engine to run a small language model of approximately 3 billion parameters on-device for local tasks, while accessing larger-scale models via a private cloud computing architecture in the cloud.79% similarUnverifiedApple Intelligence框架采用三层架构：设备端约3B参数小模型（基于OpenELM架构运行于Neural Engine）、私有云计算，以及通过模型路由分发至Google Gemini或OpenAI ChatGPT云端API76% similarUnverifiedThe Apple Intelligence architecture introduced by Apple in iOS 18 uses a small on-device model to handle everyday requests, while tasks exceeding local capabilities are forwarded to servers via Private Cloud Compute, with Apple promising not to retain user data.75% similarVerifiedApple Intelligence底层依托苹果自研的端侧小模型与Private Cloud Compute混合架构74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/566783API
curl https://kongchang.com/api/v1/knowledge/claims/566783MCP
get_claim(id=566783)