GPT4All

GPT4All is a local AI chatbot for people who want to run language models on their own desktop or laptop and keep conversations on their machine. Its LocalDocs feature lets you ask questions about your own documents without sending them to a cloud service. It suits developers, teams and individuals who want control over their models and data.

The desktop app runs on Windows, macOS and Linux, with a separate Windows ARM build. You don't need a GPU or a cloud API to run models. CPU inference works on supported computers, while NVIDIA and AMD GPUs can accelerate inference through Vulkan. Apple Silicon M-series processors are recommended for the macOS app; the Linux build supports x86-64 hardware.

GPT4All supports GGUF models, including Mistral and DeepSeek R1 distillations, and lets you customize your local assistant. LocalDocs brings document questions into the same chat application, so you can use a model with your own material as well as for general conversation. Model inference and document chat run locally without requiring a cloud connection.

For developers, a Python client built around llama.cpp provides access to local models from code. A Docker-based API server exposes an OpenAI-compatible HTTP endpoint, which lets applications use GPT4All as a model backend on hardware you control. Integrations include LangChain and the Weaviate vector database, with OpenLIT support for monitoring. The GPT4All software uses the MIT license and permits commercial use.