AI chat with a local language model –
offline and private
Qwen, Gemma, Llama, GLM and others run directly on your machine. Your conversations are stored nowhere but with you, and nobody trains on them.
From 30 € · one-time payment, no subscription · for Windows, Linux and macOS
The essentials
Models with one click
A catalogue of around 50 variants; a filter hides what will not fit your video memory.
Choose per message
For every request you can decide which model should answer.
Thinking mode
With reasoning models you see the train of thought live before the answer arrives.
Even without a GPU
Very large models can run in system memory when they do not fit into video memory.
What people ask about this
Which model should I pick?
That depends on your hardware. The model catalogue has a “fits my card” filter that hides anything too large for your video memory, so you are not guessing. Smaller models answer faster, larger ones more thoroughly.
Do I need an account?
No. There is no sign-up and no mandatory account. The licence key is bound to the device once, after which Qwirbel keeps working offline.
Are my chats used for training?
No. Conversations stay on your machine. Nothing is transmitted to us and no training happens on your content.
Can I still use cloud models?
Yes, optionally: with your own API key you can add external providers. That is entirely your choice – it is not required, and image, video and music generation stay local either way.
Qwirbel can do this too
All capabilities live in the same application – one purchase, one key.