Run Gemma 4 12B offline
Gemma 4 12B is an open AI model made by Google. Quo runs it on your own computer. You download it once. After that it works with no internet, and what you type stays on your device.
- Good at: Google’s mid-size model: clear writing in 140+ languages. Reads images. Wants a graphics card with 8 GB or more, or 16 GB of memory.
- Reads photos: Yes
- Thinks first: Yes: it works a question through step by step, and you can read its thinking.
- Code mode: Basic (desktop app)
- Licence: Apache 2.0 (see Google’s page for it on Hugging Face)
Where it runs in Quo
| Where | Download | Memory it needs | Cost |
|---|---|---|---|
| Desktop app (Mac, Windows, Linux) | 6.9 GB | 12 GB | Free |
“Memory it needs” is the computer’s memory, or the graphics card’s own memory when the model runs there. A model that doesn’t fit runs slowly or not at all; Quo checks your device and suggests one that runs well.
How to run it
On a computer
- Install the desktop app: download it, or run the one-line install shown there.
- Open Models & storage → Offline and press Download next to Gemma 4 12B.
- When it’s downloaded, start a chat. It works with Wi-Fi off.
Questions
Does Gemma 4 12B work without the internet?
Yes. Quo needs the internet only to download it. After that, Gemma 4 12B runs on your device, and your chats, documents and photos stay there.
Is it free?
Yes. In the desktop app it’s free, with no account and no limits.
Can I use it for my own work?
Gemma 4 12B is released under Apache 2.0. The full terms are on Google’s page for it on Hugging Face. Quo itself is open source under Apache 2.0.