I’m building Tinta, a journal app for Android where all the AI runs on the phone. It works in airplane mode once the models are downloaded.
You write or dictate an entry, and a small model (LFM2.5 1.2B) asks you a question to reflect further. It turns out 1.2B models are decent at asking questions, so I leaned into that. An embedding model finds older entries about the same thing and shows bits of them under the new one.
Most people using it are on budget phones running the models on the CPU, where the app provides good experience.