Successfully implemented local LLM on iPhone 16 Pro - Gemma 4 E2B operates completely offline.
ANGEWORK Inc. has successfully integrated Google's lightweight LLM "Gemma 4 E2B" into the iPhone 16 Pro, enabling on-device AI to generate Japanese responses without internet communication. In this verification, we implemented a conversation screen using SwiftUI, bundled the model within the app, addressed crashes during device startup, adjusted Japanese input, and locally saved conversation history. We confirmed functionalities such as short Japanese conversations, rephrasing of business texts, and generating item lists. Since no information is sent to the cloud, it is expected to be utilized in fields that require confidentiality, such as healthcare, manufacturing, and research, as well as in facilities without communication environments, and for reception, guidance, and input assistance. In the future, we will focus on improving speed, reducing memory usage, and advancing integration with closed-domain RAG and existing applications.

Inquiry about this news
Contact Us OnlineMore Details & Registration
Details & Registration




