展示设备端机器学习与生成式AI应用场景的演示库，支持本地模型体验与调用。
Google AI Edge Gallery 是一个面向移动设备的演示应用库，旨在展示设备端机器学习和生成式AI的强大能力。该项目允许用户在手机等设备上本地运行先进的大型语言模型（如最新的Gemma 4系列），无需连接网络即可体验高性能的AI对话、推理和创作功能，确保了数据处理的完全私密性和响应速度。 其核心功能包括：将模型升级为具备执行能力的“智能体”，可调用如维基百科查询、地图交互等工具；提供“思考模式”以可视化模型的逐步推理过程；支持多模态交互，允许用户通过图片或相机输入进行视觉问答；并具备实时音频转写与翻译能力。此外，还设有“提示词实验室”供用户测试和优化AI指令。该项目为开发者、研究者和爱好者提供了一个直观的平台，用以探索和评估未来在资源受限的边缘设备上部署高效、私有化生成式AI应用的潜力与场景。
📖 README
Google AI Edge Gallery ✨[](LICENSE)
[](https://github.com/google-ai-edge/gallery/releases)Explore, Experience, and Evaluate the Future of On-Device Generative AI with Google AI Edge.AI Edge Gallery is the premier destination for running the world's most powerful open-source Large Language Models (LLMs) on your mobile device. Experience high-performance Generative AI directly on your hardware—fully offline, private, and lightning-fast.Now Featuring: Gemma 4The latest version brings official support for the newly released Gemma 4 family. As the centerpiece of this release, Gemma 4 allows you to test the cutting edge of on-device AI. Experience advanced reasoning, logic, and creative capabilities without ever sending your data to a server.| Install the app today from Google Play | Install the app today from App Store |
| :--- | :--- |
| | |For users without Google Play access, install the apk from the latest releaseApp Preview✨ Core FeaturesAgent Skills: Transform your LLM from a conve...
📊 项目信息
- 语言
- Kotlin
- Stars
- ⭐ 18,731
- Forks
- 1,748
- 今日新增
- +897
- 排名
- #1
- 收录
- 总榜
- 趋势日期
- 2026年4月7日
- 最后推送
- 2026/4/4
📸 截图
