Using GPT4All
Updated April 2, 2024

Please Note: Screenshot and file location examples in this tutorial were created using GPT4All version 2.7.3 for Windows. Updated versions and GPT4All for Mac and Linux might appear slightly different.

Asking Questions

At the bottom of the GTP4All interface, you should see a text input labeled "Send a message...". In this input, you can type your questions, etc.

Example questions might be "Are blueberries good for my health?" or "What foods are good for cancer prevention?"

Note: If the chat input is not letting you type within it, make sure a model is currently selected and loaded.


After submitting a question, Neo LLM will process your question for a few seconds and type out a response. Your question will be directly above the response (just like a text message or live chat on social media sites).

Note: At any time during the response, you can click the "Stop generating" button.

Also if you find that reponses to your questions seem to repeat a lot or go on forever, you can increase the "Repeat Penalty" number to 2.0 instead of 1.18 (under Settings/Models tab).

You can also click the "Regenerate response " button if you want Neo LLM to answer the same question again but with a different response.

Creating/Managing Chats

In the Menu sidebar, you'll see your current chat. Using the icons, you can rename and delete chats.

You can also click the "+ New chat" button to create a new chat.

Using multiple chats is a good way to keep responses to certain questions/topics separated.

That's it. Those are the basics for using Neo LLM with GPT4All.