Gemini Nano
透過集合功能整理內容
你可以依據偏好儲存及分類內容。
有了 Gemini Nano,您就能提供豐富的生成式 AI 體驗,不必連上網路或將資料傳送至雲端。在裝置上執行 AI 是個絕佳的解決方案,適用於您最在意低成本和隱私權保護的用途。
針對裝置端用途,您可以利用 Google 的 Gemini Nano 基礎模型。Gemini Nano 會在 Android 的 AICore 系統服務中執行,該服務會運用裝置硬體,提供低推論延遲時間,並維持模型的最新狀態。
目前可透過以下方式存取 Gemini Nano:
這個頁面中的內容和程式碼範例均受《內容授權》中的授權所規範。Java 與 OpenJDK 是 Oracle 和/或其關係企業的商標或註冊商標。
上次更新時間:2025-05-21 (世界標準時間)。
[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["缺少我需要的資訊","missingTheInformationINeed","thumb-down"],["過於複雜/步驟過多","tooComplicatedTooManySteps","thumb-down"],["過時","outOfDate","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["示例/程式碼問題","samplesCodeIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間:2025-05-21 (世界標準時間)。"],[],[],null,["# Gemini Nano allows you to deliver rich generative AI experiences without needing\na network connection or sending data to the cloud. On-device AI is a great\nsolution for use-cases where low cost, and privacy safeguards are your primary\nconcerns.\n\nFor on-device use-cases, you can take advantage of Google's Gemini Nano\nfoundation model. [Gemini Nano runs in Android's AICore system service](https://android-developers.googleblog.com/2023/12/a-new-foundation-for-ai-on-android.html),\nwhich leverages device hardware to enable low inference latency and keeps the\nmodel up-to-date.\n\nAccess to Gemini Nano is currently available through:\n\n- [ML Kit GenAI APIs](/ai/gemini-nano/ml-kit-genai), which provides a high-level interface for features including: summarization, proofreading, rewrite, and image description.\n- [Google AI Edge SDK](/ai/gemini-nano/experimental), which allows experimental access for developers seeking to test enhancement of their apps with on-device AI capabilities."]]