New Book: Local LLM Setup

I’m happy to announce the release of my new book, Local LLM Setup: A Practical Guide to Running Large Language Models on Your Own Computer.

Large Language Models are usually accessed through cloud-based AI services. However, you can also run many AI models directly on your own computer. This can be useful for learning, experimentation, privacy, and building AI applications.

This practical book introduces the key concepts and tools needed to get started with local LLMs.

What You Will Learn

The book covers:

• Local LLMs and cloud LLMs

• Hardware requirements and GPU/CPU usage

• Quantization

• Choosing local AI models

• Installing and using Ollama

• Using Ollama with Python and APIs

• Building local AI chatbots

• Improving LLM performance

• Context windows and generation settings

• Tool calling and structured output

• Local RAG applications

• Embeddings and vector databases

• RAG evaluation and citations

• Fine-tuning and LoRA

• Security considerations for local AI applications

The goal is to help beginners and developers understand local LLMs and start building practical AI applications on their own computers.

Get the Book

The book is now available on Amazon in both Kindle and paperback versions. KU members can freely read this book.

If you are interested in Local LLMs, Ollama, RAG, Python, and building AI applications locally, this book may be a useful practical guide.

Thank you for supporting my books and my work in AI education. You can buy my books here, and if you need one-on-one AI coaching, read the details here.