articleworld4u
Photo: For the web interface: Georgi Gerganov and the GGML authors. For the model's res, Public domain, via Wikimedia Commons
Yes. Several capable AI models are free to download and run on an ordinary laptop, with no account and no internet once installed. Your questions never leave the machine. The trade: smaller models answer less well than the biggest paid services.
When you type into an online AI service, your words go to the company's computers. The company sets the price, the rules on what the AI will discuss, and how long it keeps the conversation. It can change any of those tomorrow.
What a company keeps is not always its own choice. In May 2025, in a copyright case brought by The New York Times, a United States court ordered OpenAI to keep ChatGPT conversations it would otherwise have deleted. The order was later narrowed, but logs saved under it stayed available to the case (OpenAI, 2025a; Bloomberg Law, 2025).
A model on your own computer has none of those problems. Nothing is sent, so nothing is stored elsewhere.
An AI model is a large file of numbers, called weights, learned from training. Most big services keep that file on their own servers. Some companies publish it so anyone can download and run it.
"Open weights" is not the same as open source. You get the finished model, not the training data or the recipe to rebuild it. The Open Source Initiative, which maintains the open source definition, draws this line clearly (Open Source Initiative, n.d.). For running a model privately, open weights is enough.
The limit is memory. A model's size in billions of parameters sets how much it needs. Compression called quantisation stores each weight in 2 to 8 bits instead of 16, cutting memory use several times over for a small loss in quality (Gerganov et al., n.d.).
| Your computer | What it runs comfortably |
|---|---|
| 8 GB of memory | Small models, around 1 to 4 billion parameters. Good for summarising, rewording and simple questions. |
| 16 GB | Models around 7 to 20 billion parameters, including gpt-oss-20b. Good for most writing and explaining. |
| 32 GB or more, or a graphics card with lots of memory | Larger models, closer to the paid services. |
As a rough guide, a model needs about its parameter count multiplied by the bits per weight, divided by eight, in bytes: an 8-billion-parameter model at 4 bits takes about 4 GB, plus room to work. Newer Macs share memory between processor and graphics, which suits this work well.
People who prefer the command line can use llama.cpp, the engine many of these tools build on (Gerganov et al., n.d.).
The biggest open models need hardware few households own. The same models can run on one powerful computer shared by a school, library, club or small business, on its own network. The people using it then decide the rules, and the conversations stay in the building.
Before you paste something private into an online AI, read its privacy page for three things: whether it trains on your chats, how long it keeps them, and who can be made to hand them over. If the answers worry you, the same question can go to a model on your own desk.
In Estonia you can. A log shows which agency read your data and why. What it looks like, who it caught, and why Australia has nothing like it.
Photo: EU2017EE Estonian Presidency, CC BY 2.0, via Wikimedia Commons
Chattanooga's city power company built gigabit fibre in 2010. Ten years on, a study counted $2.69 billion in benefits. Catalonia and Australia tried too.
Photo: Harrison Keely, CC BY 4.0, via Wikimedia Commons
One account often holds your email, photos, phone and every login. Real lockouts show what goes, why appeals fail, and what to back up today.
Photo: Santeri Viinamäki, CC BY-SA 4.0, via Wikimedia Commons
.jpg){kind=link}
