Run Large Language Models Locally in Docker | How to Use Qwen 3 with .NET SK

Question

In this video, we explore how to run Large Language Models (LLMs) locally using Docker — and connect the Qwen 3 model with .NET Semantic Kernel to build intelligent AI applications.

At CodeStreet, we focus on practical, developer-friendly tutorials that combine real-world tools with cutting-edge AI. In this hands-on session, you’ll learn exactly how to run Qwen 3 inside Docker, wire it up with .NET Semantic Kernel, and create AI-powered apps — all locally and for free.

What You’ll Learn:

• ✅ How to run Large Language Models (LLMs) locally using Docker
• ✅ How to install Qwen 3 inside a Docker container
• ✅ How to integrate Qwen 3 with .NET Semantic Kernel
• ✅ How to build intelligent apps using Qwen 3 + .NET
• ✅ How to use free Qwen 3 models for AI code generation and local experimentation

⚙️ Tools & Technologies Used:

• Docker for containerized model deployment
• Qwen 3 Model inside Docker
• .NET 9 SDK
• C# /.NET Console App for integration demo
• Visual Studio Code

Why You Should Watch:

Running AI models locally gives you more control, privacy, and flexibility — no cloud dependencies or API rate limits.

This tutorial shows you how to bring Qwen 3 to life inside Docker and connect it seamlessly to .NET Semantic Kernel, enabling you to build local AI apps that understand, reason, and generate — without external API calls.

Resources Mentioned:

• Source Code & Files: https://buymeacoffee.com/thecodestreet/e/458380
• .NET Semantic Kernel Docs: https://learn.microsoft.com/semantic-kernel
• Docker Desktop: https://www.docker.com

Who This Video Is For:

• .NET Developers exploring AI integration
• AI enthusiasts who want to run models locally
• Engineers interested in open-source LLMs
• Developers building AI apps with Semantic Kernel + Qwen3