--- title: Introducing Google AI Edge Gallery: Offline AI Model... description: Google launched AI Edge Gallery, an open-source Android app that runs AI models locally on smartphones without internet connectivity. Built on LiteRT and... canonical: https://daily.dev/posts/introducing-google-ai-edge-gallery-offline-ai-model-deployment-on-mobile-devices-jibmjzpat twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing Google AI Edge Gallery: Offline AI Model Deployment on Mobile Devices | daily.dev og:description: Google launched AI Edge Gallery, an open-source Android app that runs AI models locally on smartphones without internet connectivity. Built on LiteRT and... og:url: https://daily.dev/posts/introducing-google-ai-edge-gallery-offline-ai-model-deployment-on-mobile-devices-jibmjzpat og:image: https://api.daily.dev/og/posts/JIBMJzPat.png og:image:alt: Introducing Google AI Edge Gallery: Offline AI Model Deployment on Mobile Devices og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Introducing Google AI Edge Gallery: Offline AI Model Deployment on Mobile Devices **[Collections](https://daily.dev/sources/collections)** · 2 min read · 1 upvotes · 0 comments ## Summary Google launched AI Edge Gallery, an open-source Android app that runs AI models locally on smartphones without internet connectivity. Built on LiteRT and MediaPipe platforms, it supports Hugging Face models for tasks like image generation, text processing, and coding assistance. The app processes data entirely on-device, reducing latency and enhancing privacy while supporting various AI frameworks across CPU, GPU, and NPU hardware. ## Content Google has quietly introduced AI Edge Gallery, an innovative open-source Android app that enables users to download and run AI models on their smartphones, eliminating the need for internet connectivity. Built on Google's LiteRT platform and MediaPipe, the app supports models from Hugging Face, offering capabilities such as image generation, question answering, text generation, image analysis, coding assistance, and more. By processing data entirely on-device, the app reduces latency and enhances privacy, addressing concerns associated with cloud dependencies. AI Edge Gallery represents a strategic shift by Google towards edge computing, positioning the company as a key infrastructure provider for distributed AI systems. The application leverages a stack of tools and platforms, including MediaPipe Tasks for low-code AI integration, LiteRT for cross-platform model deployment, Model Explorer for visualization and debugging, and MediaPipe Framework for creating custom machine learning pipelines. This ecosystem supports a variety of AI models from frameworks like JAX, Keras, PyTorch, and TensorFlow, ensuring robust on-device processing across CPU, GPU, and NPU hardware. The app is particularly relevant for enterprise applications in sectors such as healthcare, finance, and IoT, where data privacy and low-latency processing are critical. Notable features of AI Edge Gallery include a Prompt Lab for text generation, a Retrieval-Augmented Generation (RAG) library for document reference, and Function Calling for automating tasks. However, it requires Developer Mode and ADB installation for setup, and currently, performance varies depending on hardware capabilities and model sizes. AI Edge Gallery is available under the Apache 2.0 license on GitHub, with iOS support anticipated in future updates. This move by Google underscores its commitment to empowering developers with tools to deploy advanced AI models directly on mobile devices, supporting both innovative application development and enhanced user privacy. ## Similar posts on daily.dev - [Don’t just attend KubeCon \+ CloudNativeCon, Merge Forward your experience\!](https://daily.dev/posts/don-t-just-attend-kubecon-cloudnativecon-merge-forward-your-experience--l0rpp73x8) · CNCF · 1 upvotes · 0 comments - [Announcing H2 2026 KCDs](https://daily.dev/posts/announcing-h2-2026-kcds-m96goajm1) · CNCF · 1 upvotes · 0 comments - [Two months of Open Community Groups](https://daily.dev/posts/two-months-of-open-community-groups-asf52zhbs) · CNCF · 0 upvotes · 0 comments - [CNCF Unveils Schedule for KubeCon \+ CloudNativeCon Europe 2026](https://daily.dev/posts/cncf-unveils-schedule-for-kubecon-cloudnativecon-europe-2026-ikhcoa5cb) · CNCF · 2 upvotes · 0 comments - [CNCF Debuts KubeCon \+ CloudNativeCon Japan 2026 Schedule](https://daily.dev/posts/cncf-debuts-kubecon-cloudnativecon-japan-2026-schedule-xp5pyudub) · CNCF · 1 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#google](https://daily.dev/tags/google), [#mobile](https://daily.dev/tags/mobile), [#android](https://daily.dev/tags/android), [#edge-computing](https://daily.dev/tags/edge-computing) [View this post on daily.dev](https://daily.dev/posts/introducing-google-ai-edge-gallery-offline-ai-model-deployment-on-mobile-devices-jibmjzpat) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Introducing Google AI Edge Gallery: Offline AI Model Deployment on Mobile Devices","url":"https://daily.dev/posts/introducing-google-ai-edge-gallery-offline-ai-model-deployment-on-mobile-devices-jibmjzpat","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-google-ai-edge-gallery-offline-ai-model-deployment-on-mobile-devices-jibmjzpat"},"datePublished":"2025-06-02T12:26:14.896Z","dateModified":"2025-06-02T21:21:32.849Z","description":"Google launched AI Edge Gallery, an open-source Android app that runs AI models locally on smartphones without internet connectivity. Built on LiteRT and...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/96e4b0a4ecaaabc2ec2d9bc93c9265fe?_a=AQAEulh","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/96e4b0a4ecaaabc2ec2d9bc93c9265fe?_a=AQAEulh","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/introducing-google-ai-edge-gallery-offline-ai-model-deployment-on-mobile-devices-jibmjzpat","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,google,mobile,android,edge-computing","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"Introducing Google AI Edge Gallery: Offline AI Model Deployment on Mobile Devices"}]} ```