Open-source assistant - Run Your Own ChatGPT Locally with Different LLM for Free on Linux, Windows and macOS
Open-source assistant or GPT4All is a free and open-source desktop app that enables you to run ChatGPT alike instance on your desktop locally.
Unlike ChatGPT it supports several LLM libraries which you can download and use totally free offline. However, it is important to note that they require several Gigabytes of space.
GPT4All is built with privacy and security first. Use LLMs with your sensitive local data without it ever leaving your device.
The app offers also a Python SDK package that can be easily in any Python projects.
With this amazing app, you can grant your local LLM access to your private, sensitive information with LocalDocs. It works without internet and no data leaves your device.
Features
- User-friendly interface
- Supports Dark mode
- Fast CPU and GPU based inference using ggml for open source LLM's
- The UI is made to look and feel like you've come to expect from a chatty gpt
- Check for updates so you can always stay fresh with latest models
- Easy to install with precompiled binaries available for all three major desktop platforms
- Multi-model - Ability to load more than one model and switch between them
- Supports both llama.cpp and gptj.cpp style models
- Model downloader in GUI featuring many popular open source models
- Settings dialog to change temp, top_p, top_k, threads, etc
- Copy your conversation to clipboard
- GPT4All allows you to run LLMs on CPUs and GPUs. It fully supports Mac M Series chips, AMD, and NVIDIA GPUs.
- GPT4All supports popular models like LLaMa, Mistral, Nous-Hermes, and hundreds more.
- Locally-running LLMs allow you to chat anytime on your laptop or device, even on the beach or in an airplane
Platforms
- Windows
- Linux
- macOS
Download
- Linux Flathub
License
MIT License