Lesson 168 · 2 min
Where AI apps live: cloud or your device
Some AI runs in big data centres far away and some runs on your own phone or laptop, and that choice affects speed, privacy, cost and quality.
Most chat assistants run in the cloud. Your message travels to a data centre full of powerful chips, a large model writes the answer, and it comes back over the internet. That gives you the strongest models, and it means your words leave your device.
On-device AI runs on your phone or computer. Smaller models can now do useful work locally: live captions, photo search, quick text suggestions, even short chats. It works without internet and keeps data at home, but the models are smaller and less capable.
Many products mix both. Simple requests are handled on the device and harder ones are sent to the cloud, sometimes with a notice. Companies can also run models on their own servers so data stays inside the business.
When you choose a tool, ask where your data goes, who can see it, and what happens when you are offline. For sensitive work, local or company-hosted models may be worth the trade in quality.
Do it now
Find one on-device feature
- 1. Turn on airplane mode on your phone.
- 2. Try voice typing, photo search or live captions and see which still work.
- 3. Those that work are running on the device. Turn airplane mode off when you are done.
Quick check
Keep going
Next →Guardrails on the way inWords from this lesson
- Edge AI
- AI that runs directly on a phone, camera or other device instead of on distant servers, so data can stay local.
- Local model
- An AI model that runs on your own computer or phone, so your data does not leave the device.
- Small language model
- A compact language model that is cheaper and faster, often good enough for focused tasks and able to run on devices.
- Data privacy
- Keeping personal or confidential information under control, including deciding what you type into AI tools and where it is stored.
- Inference
- The moment a trained model is actually used to produce an answer, as opposed to the earlier learning phase.