LLM Workshop - SWIB 2025
Learn to run powerful AI models on your own hardware
Welcome to the Local LLM Workshop! This comprehensive guide teaches you how to set up and use large language models (LLMs) locally on your personal computer. Run AI without relying on cloud services, protecting your privacy while eliminating subscription costs.
Workshop Editions
What You’ll Learn
Master LLM basics, setup Ollama with its GUI, and learn effective prompting techniques.
Automate with Python, build semantic search systems, and create RAG pipelines.
Follow along with Jupyter notebooks and build real applications.
Why Local LLMs?
- ✅ Privacy First - Your data never leaves your computer
- ✅ No Ongoing Costs - Free after initial setup
- ✅ Always Available - Works offline once models are downloaded
- ✅ Full Control - Customize everything to your needs
Get Started
Workshop Overview
This workshop is designed for both newcomers and those with prior exposure to LLMs. Through hands-on activities, you’ll learn:
Part 1: Fundamentals (2 hours)
- Understanding LLM architecture and concepts
- Setting up Ollama with its native GUI
- Choosing and running open-source models
- Writing effective prompts
Part 2: Intermediate (2 hours)
- Automating LLM interactions with Python
- Building semantic search with vector embeddings
- Creating RAG (Retrieval-Augmented Generation) systems
- Integrating external data sources
Prerequisites
Before attending, ensure you have:
- Hardware: 8 GB RAM minimum, 20 GB free storage
- OS: Windows 11, macOS 12+, or Linux
- Internet: For downloading models
- Python 3.8+: For Part 2 activities
View detailed setup instructions →
Resources
Ready to begin? Start with the current workshop →