Minggu lalu, Google diam-diam merilis aplikasi yang memungkinkan pengguna menjalankan berbagai model AI yang tersedia secara terbuka dari platform pengembangan AI Hugging Face di ponsel mereka.
Disebut Google AI Edge Gallery, aplikasi ini tersedia untuk Android dan akan segera hadir di iOS. Aplikasi ini memungkinkan pengguna untuk menemukan, mengunduh, dan menjalankan model yang kompatibel yang menghasilkan gambar, menjawab pertanyaan, menulis dan mengedit kode, dan banyak lagi. Model tersebut berjalan secara offline, tanpa memerlukan koneksi internet, memanfaatkan prosesor ponsel yang didukung.
Model AI yang berjalan di cloud sering kali lebih canggih daripada model lokal, tetapi model tersebut juga memiliki kekurangan. Beberapa pengguna mungkin khawatir mengirim data pribadi atau sensitif ke pusat data jarak jauh, atau ingin agar model tersedia tanpa perlu menemukan Wi-Fi atau koneksi seluler.
Google AI Edge Gallery, which Google is calling an “experimental Alpha release,” can be downloaded from GitHub by following these instructions. The home screen shows shortcuts to AI tasks and capabilities like “Ask Image” and “AI Chat.” Tapping on a capability pulls up a list of models suited for the task, such as Google’s Gemma 3n.
Google AI Edge Gallery also provides a “Prompt Lab” users can use to kick off “single-turn” tasks powered by models, like summarizing and rewriting text. The Prompt Lab comes with several task templates and configurable settings to fine-tune the models’ behaviors.
Your mileage may vary in terms of performance, Google warns. Modern devices with more powerful hardware will predictably run models faster, but the model size also matters. Larger models will take more time to complete a task — say, answering a question about an image — than smaller models.
Google is inviting members of the developer community to give feedback on the Google AI Edge Gallery experience. The app is under an Apache 2.0 license, meaning it can be used in most contexts — commercial or otherwise — without restriction.
