# google-ai-edge/gallery

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

Repository: https://github.com/google-ai-edge/gallery
Canonical: https://ross.abutalabs.com/products/gallery
Language: Kotlin
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T23:09:05+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 37
- inputs: {"age_days": 520, "days_push": 7, "days_rel": 23, "gap_med": 5, "n_releases_24m": 26}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 24565, forks 2650 (observed 2026-08-28T04:11:37.496345+00:00)

## What it is
Google AI Edge Gallery is a mobile and desktop application for running open-source large language models like Gemma entirely on-device, offline. It showcases on-device generative AI use cases and lets users explore, experience, and evaluate models locally with full privacy.

## Use cases
- run LLMs offline on my phone
- try Gemma models locally without a server
- private on-device AI chat app
- test on-device generative AI use cases
- evaluate small language models on mobile hardware
- chat with an AI without sending data to the cloud

## When to choose
- you want to run open-source LLMs fully offline on Android, iOS, or macOS
- privacy matters and you don't want data sent to servers
- you want to experiment with Gemma and other on-device models
- you need a reference app for on-device GenAI with Google AI Edge

## When to avoid
- you need cloud-scale models or server-side inference
- you want a library or SDK to embed in your own app rather than a ready-made app
- you need desktop Linux or Windows support

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, chatbot, machine-learning
- domain: large-language-models, artificial-intelligence, mobile-development, privacy
- platform: jvm
- tags: on-device-ai, genai, offline-llm, gemma, google-ai-edge, local-inference, android, ios, macos, mobile, desktop

## Member repositories
- google-ai-edge/gallery (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:37.496345+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:56:12.199334+00:00, confidence not recorded.
  - readme: https://github.com/google-ai-edge/gallery (fetched 2026-08-28T04:11:37.496345+00:00, sha 3dbb0f1088e1)
- Data as of 2026-08-30T08:39:29.467469+00:00.