Effortless Local Installation of DeepSeek R1 with Zero Data Sharing

DeepSeek R1 is a powerful AI model, and running it locally on your machine ensures that your data remains private. This guide walks you through installing DeepSeek R1 using Ollama — an open-source tool for running large language models locally — and provides an optional setup for a web-based interface with Docker.

Step 1: Install Ollama

Ollama is designed to help you run large language models on your local system without relying on cloud services. To install Ollama:

1. Visit the Official Website:
    Go to the Ollama website and download the installer that matches your operating system.
2. Run the Installer:
    Execute the downloaded installer and follow the on-screen instructions to complete the installation process.

Step 2: Download and Run the DeepSeek R1 Model

Once Ollama is installed, you can download and run the DeepSeek R1 model with a few simple commands.

1. Open Your Terminal or Command Prompt:
    Access the command-line interface on your computer.
2. Download and Run DeepSeek R1:
    Execute the following command to download the 7B parameter version of the model:

ollama run deepseek-r1:7b

• This command initiates the download of the DeepSeek R1 model.
• If your needs or system capabilities differ, you can choose alternative model sizes (e.g., 1.5b, 14b).

1. Automatic Launch:
    Once the download is complete, DeepSeek R1 will automatically launch, allowing you to start interacting with the model immediately.

Important Considerations

• Download Size:
   The model is approximately 4.7GB in size. Depending on your internet connection, the download may take some time.
• System Compatibility:
   Ensure that your system meets the necessary requirements for the selected model size.
• Privacy Assurance:
   Running DeepSeek R1 locally guarantees that all data remains on your computer. No data is transmitted externally, preserving your privacy.

Optional: Set Up Open WebUI for a User-Friendly Interface

If you prefer a graphical interface to interact with DeepSeek R1, you can use Open WebUI. Follow these steps to set it up using Docker:

1. Install Docker:
    Make sure Docker is installed on your machine.
2. Run the Docker Command:
    Execute the following command to install and run Open WebUI:

docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

1. Access the WebUI:
    Open your web browser and navigate to http://localhost:3000 to begin using DeepSeek R1 through the web interface.