google-ai-edge/gallery

Health v2 · maintenance only

Adoption not part of the score

25018 stars · 2747 forks observed · 2026-10-19

What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-12, confidence 0.97

Google AI Edge Gallery is a mobile and desktop app that lets you run large language models and multimodal AI directly on your device. It provides offline, private generative AI capabilities such as chat, image and video search, and embedding generation.

Use cases

• Run a powerful LLM locally on a phone without internet connectivity.
• Perform private, offline AI chat or text generation on a mobile device.
• Search images, audio, or video content on-device using embedding-based semantic search.
• Generate embeddings for personal documents and query them locally.
• Use on-device computer‑vision models to analyze photos or video clips without sending data to the cloud.

When to choose

• You need AI capabilities that work completely offline and keep data on the device.
• Privacy is a top concern and you cannot send user data to external servers.
• You want a ready‑to‑install app for Android, iOS, or macOS with minimal setup.
• Your use case involves on‑device multimodal search or local LLM inference.

When to avoid

• You require the latest, largest models that exceed the device’s hardware limits.
• You need to serve many concurrent users or scale across a server farm.
• Your workflow depends on continuous model updates that are only available in cloud services.

Facets

application · maturity active

llm-inference rag computer-vision video-processing search-engine artificial-intelligence large-language-models computer-vision on-device-ml generative-ai offline privacy multimodal-search retrieval-augmented-generation video android ios macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="google-ai-edge/gallery")