How to Run DeepSeek Locally (NO Internet) Without Sending Your Data to China

4 min readFeb 6, 2025

DeepSeek R1 launched on January 22nd, 2025, and it took the internet by storm. It became one of the most downloaded AI apps, even topping Apple’s app store. The release had a massive impact, shaking the tech industry. Nvidia reportedly lost $600 billion in market value, marking the biggest stock drop in history. The US Stock market also lose trillions of dollars.

But with all the hype, concerns about privacy quickly emerged. Since DeepSeek is developed by a Chinese company, many users worry about their data being sent to China. What if I told you that you can run DeepSeek completely offline on your computer? No internet connection required, meaning no risk of data leakage.

Good news: It’s easy to set up! In just four steps, you can have DeepSeek running locally on your Mac, Windows, or Linux machine.

Step 1: Download and Install Ollama

Ollama is a powerful tool that lets you run AI models locally on your machine.

Go to ollama.com/download
Download the installer that matches your operating system (Mac, Windows, or Linux).
Run the installer and follow the on-screen instructions.

Once installed, verify that Ollama is working by running the command below on your terminal:

ollama --version

If the installation was successful, you should see the version number displayed.

Step 2: Install Open WebUI

Open WebUI provides a user-friendly interface to interact with DeepSeek instead of using the command line.

There are two ways to install Open WebUI: via Python pip or Docker. For simplicity, we’ll use Python.

First, Install Python and Pip

If you don’t have Python and pip installed, follow these steps:

Download Python from python.org/downloads
Install Python, ensuring you check the box “Add Python to PATH” during installation.
Verify Python installation by running:

python --version

4. Verify pip installation by running:

pip --version

If you have have any issue installing python and pip. There are lot of people that must have faced the same issue. You can just google it or check on youtube. It is very easy to install python and pip.

Install Open WebUI

Now, install Open WebUI using pip:

pip install open-webui

This will download and install Open WebUI on your system.

Step 3: Download DeepSeek Model

DeepSeek comes in multiple sizes, from 1.5B to 671B parameters. Here’s what you need to know:

More parameters = better AI responses
More parameters = higher resource demand on your computer
671B is too large for most personal computers!

I recommend starting with the 7B model, which balances performance and system requirements.

To download and run DeepSeek locally, use the following command:

ollama run deepseek-r1:7b

This command downloads the model and starts DeepSeek on your machine.

If you prefer a smaller model, here’s an example for 1.5B:

ollama run deepseek-r1:1.5b

Once downloaded, you can already start using DeepSeek from the command line, but let’s make it more user-friendly with Open WebUI.

Step 4: Run Open WebUI

Now that everything is installed, it’s time to launch the graphical interface.

Run this command to start Open WebUI:

open-webui serve

This will start the interface on your local machine. Open your browser and go to:

http://0.0.0.0:8080

You should see DeepSeek running in Open WebUI. 🎉

Final Test: Run DeepSeek Completely Offline

To prove that your data isn’t being sent anywhere, turn off your Wi-Fi and test DeepSeek. If it still works, congratulations you now have a fully local AI chatbot that ensures your privacy.

Now you have one of the best AI models in the world running entirely on your own computer, without internet access. No more privacy concerns!

If you found this guide helpful, subscribe to my platform Dont-Fear-AI.com for more AI tutorials. Have questions or feedback? Feel free to reach out on X (@trojrobert) or LinkedIn (John Robert).

Originally published at https://dont-fear-ai.com.