Run DeepSeek Locally with Docker on Windows | Fast AI Setup (No Internet Needed!)
☕ If you enjoy my tutorials, I'd be so grateful if you could Buy Me A Coffee! https://buymeacoffee.com/janpiapiae
In this tutorial, I’ll walk you through the steps to set up a local AI server using DeepSeek and Docker on Windows 11. You’ll learn how to enable virtualization, install Docker, configure WebUI, and load a language model to run your very own AI bot — all without needing an internet connection. Perfect for those who want complete control over their AI environment!
Let me know if you have any questions or suggestions in the comments!
💻 DeepSeek on Windows PC Locally 💻
📌 1. Windows Features - open optionalfeatures (Windows 11) ⚙️.
Checkbox - Check the "Virtual Machine Platform" option ✅.
Reboot PC 🔄.
📌 2. Go to 🔗 https://ollama.com/ and download the Windows version 📥.
📌 3. Go to 🔗 https://docs.docker.com/ Get Docker Docker Desktop for Windows - x86_64 📖.
Install and reboot the PC 🔧.
After rebooting, you will see a command window pop-up asking you to press any key to update WSL (Windows Subsystem for Linux) ⏳.
You will also see the Docker Desktop Wizard asking you to log in to your account 🖥️.
4. Go to docs.openwebui.com / Getting Started / Quick Start 📚.
Press Win+R, then type cmd ⌨️.
Run the following commands:
docker pull ghcr.io/open-webui/open-webui:main
docker run -d -p 3000:8080 -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:main
For Nvidia GPU support, add --gpus all to the docker run command:
docker run -d -p 3000:8080 -e WEBUI_AUTH=False -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:main
docker run -d -p 3000:8080 -e WEBUI_AUTH=False -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:main
To stop the Docker container:
docker rm -f open-webui
📌 5. Go back to the Docker Desktop app 🖱️.
You will see that your Docker container is running 🚀.
If you click on the port number, you will see the Open WebUI 🌐.
📌 6. Adding Language Models
Go to 🔗 https://ollama.com/ Models 🧠.
Try: deepseek-r1:7b (7 billion parameters) 🔢.
Go back to the WebUI and choose the model 🔍.
00:00 Intro
00:27 Enabling Virtualization
00:48 Desktop Docker
02:07 WebUI
03:05 Large Language Model
04:09 Final tests AI
Music I use:
Cinematic-Piano-Free-No-Copyright-Music-
Liborio-Conti:
05-What-Ive-Found
#DeepSeek, #Local AI, #AI Without Internet, #Docker AI Setup, #docker