Google AI Edge Gallery
A mobile and Mac app from Google for downloading and running generative AI models on-device.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
About Google AI Edge Gallery
Google AI Edge Gallery lets you download open models such as the Gemma 4 family and run them directly on a phone or Mac, without sending prompts to a server. Once a model is downloaded, it works offline.
Features include multi-turn AI chat with a Thinking Mode that shows the model's step-by-step reasoning, and Agent Skills that add tools such as Wikipedia lookups, interactive maps and visual summary cards. It is available from Google Play and the App Store, with an APK in the GitHub releases for devices without Google Play.
Strengths
- Runs models fully on the device, with no data sent to a server
- Official support for Google's Gemma 4 models
- Agent Skills add tools such as Wikipedia and maps
- APK available for phones without Google Play
Limitations
- Performance depends heavily on the phone's hardware
- Limited to the models on the app's allowlist
- Positioned as a showcase and evaluation app rather than a full assistant
Details
- Pricing
- FreeFree and open source under the Apache 2.0 licence.
- License
- Apache-2.0
- Developer
- Platforms
- macOS, Android, iOS
- How it runs
- Downloadable app
- Works offline
- Yes
- Best suited for
- Trying open language models offline on an Android phone, iPhone or Mac
- Categories
- Local AI tools, AI assistants
- Last verified
- Added
Alternatives to Google AI Edge Gallery
Compare allSoftware that can replace Google AI Edge Gallery for an important use case, and what changes if you switch.
PocketPal AI
A mobile app for Android and iOS that downloads small language models and runs them on the phone.
PocketPal AI downloads small language models and runs them on Android and iOS phones, but it has no Mac version and is not listed as open source.
ChatterUI
An Android front end for running language models on the phone or connecting to API providers.
ChatterUI runs models on Android phones and can also connect to API providers you choose, but it is Android only and its licence is not stated.
Maid
A free, open-source app for chatting with llama.cpp models locally and remote AI providers.
Maid is an open-source Android app that runs llama.cpp models locally and can also connect to Ollama servers or hosted providers with their own API keys.
Layla
An offline AI assistant app that runs language models directly on Android and iOS devices.
Layla runs models offline on Android and iOS with character creation for role-play chats, but it is closed source, freemium and has no Mac version.
Private LLM
An offline AI chat app for iPhone, iPad and Mac that runs open language models on the device.
Private LLM is a paid, closed-source offline chat app for iPhone, iPad and Mac with Siri and Shortcuts integration, and it has no Android version.
Enclave AI
An iPhone, iPad and Mac app for chatting with open-source AI models that run offline on the device.
Enclave AI runs models offline on iPhone, iPad and Mac with local voice chat and PDF chat, but it is closed source and Apple only.
fullmoon
A free app for chatting with small local language models on iPhone, iPad, Mac and Vision Pro.
fullmoon is a free offline chat app for Apple silicon iPhone, iPad, Mac and Vision Pro using MLX, limited to a small set of small models.
LLMFarm
An iOS and macOS app for running large language models offline on the device using GGML.
LLMFarm is an open-source iOS and macOS app running GGML models offline without an account, but it is Apple only and maintained by a single developer.
Google AI Edge Gallery as an alternative
Listings that name Google AI Edge Gallery as an alternative.
Google Gemini
Google's multimodal AI assistant, formerly Bard, integrated with other Google services.
Google AI Edge Gallery runs Gemma models fully on an Android phone, iPhone or Mac under Apache-2.0, as a showcase app rather than a full assistant.
Similar software
Related functionality, not necessarily a direct replacement.
llama.cpp
The C++ engine most local AI apps are built on, running language models on ordinary hardware.
MLC LLM
A compiler and inference engine for running large language models natively across GPUs, phones and browsers.
Ollama App
A cross-platform chat client for talking to language models running on an Ollama server.
LM Studio
A polished desktop app for downloading, running and chatting with local language models, with an OpenAI-compatible server built in.
