GPT4All
A local chat desktop app with a long history, aimed squarely at ordinary hardware and people who do not want a terminal.
- Self-hosted
- Active
- Allowed adult content
- Open source
At a glance
- Where it runs
- Self-hostedYou run it on your own machine. Nothing leaves it unless you send it.
- Adult content
- AllowedAdult content is permitted within the published rules.
- Trains on your content
- Opt-inOnly if you turn it on.
- Status
- ActiveMaintained and working today.
- Account needed
- No
- Licence
- MIT
- Cost
- Free and open source.
- What it keeps
- Local. An optional opt-in setting shares chats with the publisher for research; it is off unless you turn it on.
What it takes to run
- Graphics memory
- No GPU needed
- System memory
- 8 GB, 16 GB recommended
- Disk
- about 15 GB
- Runs on
- Linux, macOS, Windows
Find what fits your machine on the tools page — pick your hardware from the first menu.
One of the earliest projects to make running a language model on a normal computer a download rather than a build, and still maintained. It leans towards CPU-friendly models and has a document-chat feature that indexes a local folder.
It is a reasonable pick if Ollama's command line and LM Studio's closed source both put you off.
Worth knowing before you start
- Opt-in data sharing exists It is off by default, but it is a setting in the application — check it after install.
What it does
- Runs well on CPU
- Chat with local documents
- Model downloader
Signs of life
Checked automatically. These are the only figures on this page a machine wrote, and they say when they were taken.
- Last answered
- Yes, 3 hours ago Its website responded when we asked.
- Stars on GitHub
- 77,396 8,290 forks.
- Last commit
- 476 days ago2025-05-27 20:05 UTC
- Latest release
- v3.10.0
Categories
Something here wrong or out of date? Tell us — this page is only worth having if it is right.