9 Sources
[1]
Google quietly released an app that lets you download and run AI models locally | TechCrunch
Last week, Google quietly released an app that lets users run a range of openly available AI models from the AI dev platform Hugging Face on their phones. Called Google AI Edge Gallery, the app is available for Android and will soon come to iOS. It allows users to find, download, and run
[2]
This new Google app lets you use AI on your phone without the internet - here's how
You want to use AI on your phone, but you're stuck in a dead zone. Typically, that won't work, as those large language models require an internet connection. Aah, but wait. Google has cooked up an app designed to surmount that barrier. Available now for Android and coming soon to iOS, the
[3]
This Google experimental app lets you run powerful AI models without Wi-Fi
Forget Google Keep, OneNote and Evernote, 5 reasons NotebookLM is the future of note-taking Summary Google has quietly launched an experimental app called AI Edge Gallery, allowing users to run AI models on their devices without needing a Wi-Fi or cellular connection. The app supports several
[4]
Google quietly launches AI Edge Gallery, letting Android phones run AI without the cloud
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Google has quietly released an experimental Android application that enables users to run sophisticated artificial intelligence models directly on their smartphones
[5]
Google's Latest App Lets Your Phone Run AI in Your Pocket -- Entirely Offline - Decrypt
Google has released a new app that nobody asked for, but everyone wants to try. The AI Edge Gallery, which launched quietly on May 31, puts artificial intelligence directly on your smartphone -- no cloud, no internet, and no sharing your data with Big Tech's servers. The experimental app --
[6]
Offline AI just went mainstream with Google's new tool
Google released the Google AI Edge Gallery app last week, enabling users to download and run AI models from Hugging Face on their phones. The Android app, with an iOS version forthcoming, facilitates offline AI task execution. The Google AI Edge Gallery, labeled an "experimental Alpha release," is
[7]
This New Google App Can Run AI Models Locally On Your Device
Google's app will find AI models that are compatible to run on the device Google AI Edge Gallery, a new app for Android that allows users to experience running artificial intelligence (AI) models locally on a device, was released on Sunday. The Mountain View-based tech giant says the experimental
[8]
Google lets Android phones run AI models without internet
Google has introduced the AI Edge Gallery app for Android, enabling users to run AI models from Hugging Face locally on their smartphones without an internet connection. This experimental release allows users to access tools like 'Ask Image' and 'AI Chat,' utilizing models such as Google's Gemma
[9]
Google Debuts App to Let Users Run AI Models on Their Phones | PYMNTS.com
The tool lets users find, download and run compatible models that do things like generating images, answering questions, or writing and editing code. The models run offline using phones' processors, without any need for an internet connection. The report noted that while AI models running in the
Share
Copy Link
Google has released an experimental app called AI Edge Gallery that allows users to download and run AI models locally on their Android devices without an internet connection, offering privacy and offline functionality.
Google has quietly released an experimental application called AI Edge Gallery, marking a significant step in the company's push towards edge computing and privacy-focused AI deployment
1
2
. This innovative app allows users to download and run sophisticated AI models directly on their Android smartphones without requiring an internet connection3
.
Source: ZDNet
AI Edge Gallery enables users to access a range of AI capabilities offline, including:
The app supports various open-source AI models from platforms like Hugging Face, including Google's own Gemma 3n
1
4
. Users can switch between different models to compare performance and capabilities, with real-time benchmarks showing metrics like time-to-first-token and decode speed4
.The application builds on Google's LiteRT platform (formerly TensorFlow Lite) and MediaPipe frameworks, which are optimized for running AI models on resource-constrained mobile devices
4
. At its core, the app utilizes Google's Gemma 3 model, a compact 529-megabyte language model capable of processing up to 2,585 tokens per second during prefill inference on mobile GPUs4
.By keeping all data processing local, AI Edge Gallery addresses growing concerns about data privacy in AI applications
4
5
. This approach is particularly valuable for sectors like healthcare and finance, where data sensitivity requirements often limit cloud AI adoption4
. However, the shift to on-device processing introduces new security considerations, such as protecting the devices themselves and the AI models they contain4
.
Source: VentureBeat
Google's move comes amid intensifying competition in the mobile AI space, with companies like Apple, Qualcomm, and Samsung already offering embedded AI capabilities in their devices
4
. However, Google's approach differs by focusing on platform infrastructure rather than proprietary features, positioning itself as the foundation layer for mobile AI applications4
.Related Stories
Early tests on devices like the Samsung Galaxy S24 Ultra have shown promising results, with performance comparable to what GPT-3.5 delivered at launch
5
. The app offers three core capabilities: AI Chat, Ask Image, and Prompt Lab2
5
. However, it currently faces limitations, such as a restricted selection of compatible models and a context window of 4096 tokens, which may feel limited by 2025 standards5
.The local processing approach offered by AI Edge Gallery could transform the AI privacy equation, allowing organizations to leverage powerful AI capabilities while maintaining data protection
4
. This technology could be particularly useful for:5

Source: Gadgets 360
As Google continues to develop and refine this technology, it has the potential to democratize access to advanced AI capabilities while addressing the growing demand for privacy-conscious AI solutions
1
4
5
.Summarized by
Navi
[1]
[4]
1
Technology

2
Technology

3
Policy and Regulation
