What does Fullmoon do and what problem does it solve?
Fullmoon is an open-source app that enables users to run local large language models directly on Apple devices. It solves the problem of needing internet access for AI by offering completely offline functionality and optimized performance for Apple silicon.
What features, platforms, and integrations does Fullmoon offer?
Fullmoon offers features like theme and font personalization, system prompt adjustment, and Shortcut integration for getting model outputs to use with other actions. It runs on iOS, iPadOS, macOS, and visionOS, and is optimized for Apple silicon.
What specific models does Fullmoon support and what are their technical specifications?
Fullmoon supports several models, including Llama-3.2-1B-Instruct-4bit (193M params, 0.7 GB), Llama-3.2-3B-Instruct-4bit (502M params, 1.8 GB), DeepSeek-R1-Distill-Qwen-1.5B-4bit (278M params, 1.0 GB), and DeepSeek-R1-Distill-Qwen-1.5B-8bit (500M params, 1.9 GB).
How is Fullmoon priced or packaged?
Fullmoon is free, open source, and private, with no evidence of a paid pricing model or packaging.
What is Fullmoon used for and in what situations?
Fullmoon is used for chatting with private and local large language models. It is designed for use in situations where you don't have internet, as it works fully offline and runs models directly on the device.
Who is Fullmoon for?
Fullmoon is for users seeking private and local large language models, with a focus on developers and privacy-focused individuals due to its offline, on-device AI inference.
What is Fullmoon?
Fullmoon is a free, open-source application that enables users to run local large language models on Apple devices for private, offline AI conversations.