Local LLM (GPT4All)

GPT4All is a project that lets users run large language models privately on everyday desktops and laptops, without API calls or GPUs, by downloading an application. The download page lists installers for Windows, Windows ARM, macOS and Ubuntu, with the Windows and Linux builds requiring Intel Core i3 2nd Gen or AMD Bulldozer or better, and the macOS build requiring Monterey 12.6 or newer. A Python client built around llama.cpp implementations is also available, and the release history lists V3.0.0 on July 2nd, 2024, with a redesigned chat UI and expanded model support.