GPT4All

A local chat desktop app with a long history, aimed squarely at ordinary hardware and people who do not want a terminal.

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

What it does

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Something here wrong or out of date?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.