How to Easily Install DeepSeek R1 on Your Computer (No Data Sharing Required)

Over the last few days, DeepSeek has taken the AI world by storm. Some have dubbed it the “ChatGPT killer,” while others have raised concerns over its alleged pro-China censorship. Whatever your views, the best way to form an opinion is to try it yourself—locally and securely.

In this tutorial, you’ll learn how to install DeepSeek R1 on your own computer in just 3 simple steps—all while keeping your data private. No need to rely on cloud APIs or share your sensitive inputs with external servers.

Prefer video? Check out our 2-minute visual walk-through on this installation process.

This guide is part of Artificial Corner, a growing newsletter where we break down AI in plain English. Join thousands of tech enthusiasts, programmers, and professionals tapping into the potential of AI technology—all while receiving free cheat sheets and tools.

Step 1: Install Ollama

First, we need to install Ollama—an open-source platform designed to run large language models (LLMs) locally on your machine. It’s user-friendly, powerful, and completely private.

1. Head over to the official Ollama website.
2. Click the Download button and select your operating system.
3. After downloading, unzip the file and open the installer.
4. You’ll be greeted by a “Welcome to Ollama” setup screen. Just click Next to proceed.
5. Be sure to install the command line interface (CLI) when prompted.
6. Once installation is complete, click Finish.

You now have Ollama set up on your system, providing a secure base to run models like DeepSeek R1.

Step 2: Install DeepSeek R1 Using Your Terminal

Now that you have Ollama installed, the next step is to load DeepSeek R1 into it.

1. Visit the Ollama model library.
2. In the search bar, type deepseek-r1 and press enter.
3. Select the version that works best for your computer. DeepSeek R1 is available in multiple sizes—optimized for both high-end and mid-range systems.
4. Open your terminal or command prompt.
5. Enter the following command to install the model:
   ollama run deepseek-r1
6. The model will begin downloading. Depending on the model size and your internet speed, this may take a few minutes.

Once installed, DeepSeek R1 will launch directly in your terminal, allowing you to interact with it just like ChatGPT—but running entirely on your system.

Step 3: Launch DeepSeek UI and Start Chatting

While you can interact with DeepSeek via the terminal, many users prefer a graphical user interface (GUI) for convenience. You can connect DeepSeek R1 to any existing open-source interface that supports Ollama APIs.

One recommended tool is Chatbot UI. It offers a sleek, customizable frontend for your local models.

1. Download the Chatbot UI project from GitHub.
2. Follow the setup instructions to connect it with Ollama.
3. Point the backend API to localhost where DeepSeek is running.
4. Start chatting with DeepSeek using an intuitive web-based interface!

Why Install DeepSeek R1 Locally?

• Data Privacy: No prompts or conversations are shared with external servers.
• Faster Response Times: Experience near-instant responses without round-trip latency.
• Open-Source Control: Customize, tweak, and optimize to your heart’s content.

System Requirements for DeepSeek R1

DeepSeek R1 is a large-scale language model, so performance depends on your hardware. Here’s a basic guideline:

• Minimum: 16GB RAM, Modern CPU, SSD
• Recommended: Dedicated GPU (NVIDIA 30xx or newer), 32GB+ RAM

Choose the smaller versions of the model for better performance on low- to mid-range systems.

Final Thoughts

DeepSeek R1 represents a major leap forward in the local AI space. Thanks to platforms like Ollama, anyone can now run powerful LLMs without compromising data privacy or relying on expensive APIs.

So why wait? Test DeepSeek R1 on your machine today and see what all the buzz is about—on your own terms.

For more AI tutorials, model reviews, and helpful tools, don’t forget to subscribe to the Artificial Corner newsletter.

Happy experimenting!