GPT4All
Run local LLMs on any device
77.3k|stable|v3.10.0
Download for Windows
Download .zip — extract and run
How to install
1Download the file above
2Extract the .zip file
3Run gpt4all.exe
Offline inference — Run language models without internet or API calls.
Multi-platform support — Works on Windows, macOS, and Linux with CPU-only requirements.
Python bindings — Integrate models into applications via pip-installable package.
LocalDocs feature — Chat privately with your local documents and data.
Model library — Access multiple open-source models including Llama and Mistral.
GPT4All gives you a desktop app and Python library to run quantized language models on consumer hardware without GPUs. The chat interface includes features like LocalDocs for document Q&A and works offline completely. It's actively maintained with frequent model and feature updates.
Intel Core i3 2nd Gen or better (x86-64); macOS Monterey 12.6+; Windows ARM builds for Snapdragon/SQ processors
Source on GitHub
pavilion