Great project for demystifying LLMs. Running one locally really makes the mechanics click — I use aiME which runs Qwen/Mistral/Gemma fully on my phone, no cloud needed. Seeing inference happen completely on-device without any network calls makes it feel much more tangible.

Website : https://coticsy.com/aime.html

iOS: https://apps.apple.com/us/app/aime-ondevice-ai/id6754805828

Android: https://play.google.com/store/apps/details?id=com.coticsy.ll...