How to run your first open‑source LLM from DeepSeek on a home PC

Learn how to download and chat with a powerful, completely private AI model on your own Windows or Mac laptop.

4 min read·4 steps·28 June 2026

Have you ever wanted to chat with a powerful AI without sending your private conversations off to a tech company's distant servers? This step-by-step guide will show you how to download and run DeepSeek's open-source AI entirely on your own laptop, keeping your data completely secure and offline.

✅ Before you start

A modern computer: A Windows PC or Mac laptop (ideally made in the last few years with at least 8GB of memory/RAM).
A stable internet connection: You will need to download a few gigabytes of files.
Hard drive space: Around 5GB of free storage space.

Download the runner app (Ollama)

To run an AI on your computer, you need a translation helper that lets your hardware speak to the AI file. We will use a free, trusted tool called Ollama. Think of Ollama like a video player, while the DeepSeek AI is the movie file you want to play.

Visit the official Ollama website in your web browser, click the download button for your operating system (Mac or Windows), and install the app just like you would with any other software.

Open your computer's command centre

To tell Ollama to fetch and start the DeepSeek model, we need to use a simple text command.

On Windows: Click your Start menu, type "cmd", and open the Command Prompt app.
On a Mac: Press Command + Space on your keyboard, type "Terminal", and press Enter.

This opens a simple, retro-looking window where you can type commands directly to your computer.

Download and run DeepSeek

Now we will fetch a lightweight version of DeepSeek's model. This is an LLM (large language model — the digital engine or brain that powers a chatbot). We will use a smaller version of DeepSeek-R1 that is specifically designed to run smoothly on everyday home computers.

In your Command Prompt or Terminal window, type the following command exactly as shown and press Enter:

💬 Try typing this`ollama run deepseek-r1:1.5b`➤

Your computer will automatically start downloading the model files. You will see a progress bar in the window. Once the download finishes, a chat prompt will appear.

Start your private conversation

You are now connected to an offline AI running entirely on your local machine! You can type a question, hit Enter, and watch the AI respond.

💬 Try typing this`What are three fun activities to do on a rainy weekend afternoon?`➤

Watch the AI think through the process and write out the response word by word. When you are finished and want to close the chat, simply type /bye and press Enter.

⚠️ Common mistakes

Watch out for slow typing speeds: If the AI takes a very long time to generate a reply, your computer may be running low on active memory. Try closing web browsers, games, or video editing software to free up your computer's RAM.
Watch out for massive files: Avoid downloading the giant "70b" versions of models unless you have a high-end gaming computer. Stick to the "1.5b" or "8b" versions. The "b" stands for billions of parameters, which are like the neural connections in the AI's brain; fewer parameters run much faster on ordinary laptops.

✦ Original step-by-step guide by AI World Co.'s AI editorial team. Written in plain language, reviewed for accuracy.

← Back to all stories