Support

How can we help?

Got a problem? We’ve got you. LokalMind is made by one developer who reads every message.

Frequently asked questions

Do I need internet to chat?

No. Once a model is downloaded, LokalMind works completely offline. Internet is only used to download models and app updates.

Why is the app slow on my device?

Larger models (4B) need more RAM. Try a smaller model like Qwen 3.5 0.8B for faster responses on older devices.

How do I delete a model?

Go to the Models tab → tap the model → Delete. This frees up storage immediately.

Where is my chat data stored?

Everything — chats, settings, memories — is stored locally on your device. Nothing is sent to any server.

What is a system prompt?

A system prompt tells the AI how to behave — its tone, expertise, and rules. LokalMind lets you write your own for each mode in Profile → AI Behavior.

The model failed to load. What do I do?

Try closing and reopening the app. If it persists, delete and re-download the model from the Models tab.

How do I reset everything?

Profile → Erase All Data. This wipes all chats, settings, memories, and downloaded models from your device.

Feature requests

Have an idea? Open a GitHub Discussion — the roadmap is shaped in public.

Support the project

LokalMind is free and open source. If it’s useful to you, you can help keep it going: