The first time you launch the application, you will need to download the Gemma 4 E2B file (approximately 3GB). Gemma 4 is a large-scale language model developed by Google DeepMind as part of an open AI model family.
Selecting a message from the four buttons at the bottom of the screen will add it to the chat as your message, and replies will be displayed.
The conversation history is saved on your device and will not be leaked externally.
Due to the nature of the model, hallucinations are frequent. Please play with it in a lighthearted manner and do not take the conversations seriously.
A chat app that runs a large-scale language model (LLM, Gemma 4 E2B native execution) on the device and allows users to advance conversations using four selection buttons.