Udemy
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Run LLMs Locally with Python: Build Private AI Apps
Rating: 4.4 out of 5(22 ratings)
112 students

Run LLMs Locally with Python: Build Private AI Apps

Learn local LLMs, RAG, agents and offline AI on Windows, Mac and Linux
Created byGanesh S
Last updated 9/2026
English

What you'll learn

  • Run open-source LLMs locally on Windows, macOS, and Linux without relying on cloud APIs
  • Set up a local LLM development environment using Python, Poetry, and local model runtimes
  • Build Python applications that communicate with and control locally running LLMs
  • Apply prompt engineering, roles, tokens, context windows, and multi-turn conversations to local LLM applications
  • Build LLM-powered tools and a customer support agent using function calling
  • Build a practical Retrieval-Augmented Generation (RAG) application using local LLMs and external knowledge

Course content

2 sections • 16 lectures • 3h 48m total length

  • Introduction to Running LLMs Locally7:49

    Get a quick overview of the course, its structure, learning outcomes, and what you can expect by the end—including running LLMs locally without cloud dependency.

  • Hardware Requirements for Running LLMs Locally3:08

    Learn the recommended CPU, RAM, GPU, and disk requirements to run modern language models efficiently on your machine — without relying on the cloud. We'll also cover real-world performance tips and tradeoffs.

  • See a Local LLM Running Offline on a Mac5:38

    See it in action! This lecture gives you a sneak peek of the course’s final result — a fully functional, offline LLM running on a local Mac. Visualize what you'll build and get inspired to follow the setup journey.

  • Tools for Running LLMs Locally6:13

    Explore the lightweight, open-source tooling (like Ollama or alternatives) that powers offline LLM execution. Learn about model variants, architecture support, and how it works under the hood.

  • Run a Local LLM on Windows11:45

    Follow step-by-step instructions to install, configure, and verify your local LLM setup on a Windows machine.

  • Run a Local LLM on Ubuntu Linux12:58

    Learn how to set up and run the local LLM model on Ubuntu/Linux-based systems, including dealing with common environment and dependency issues.

  • Run a Local LLM on macOS10:32

    Mac users—this one’s for you. Get a hands-on walkthrough for setting up your model locally and troubleshooting any OS-specific issues.

Requirements

  • Knowledge of Python programming — you should know how to install python, write, debug and run Python scripts.
  • Familiarity with the command line or terminal — you’ll use basic commands during setup and testing.
  • A computer running Windows, macOS, or Linux — the course includes platform-specific setup instructions.
  • At least 8GB of RAM (16GB recommended) — running language models locally requires a reasonable amount of memory.
  • A stable internet connection for the initial setup only — after that, everything runs 100% offline.
  • No prior experience with LLMs, AI, or machine learning is required — all key concepts are explained with hands-on examples.

Description

This course teaches you how to run LLMs locally with Python and build practical AI applications without depending on cloud APIs, subscriptions, or sending your data to external services.

You’ll set up a local LLM environment on Windows, macOS, or Linux, connect to local models using Python, and progressively build real LLM capabilities including prompting, conversations, tools, function calling, and Retrieval-Augmented Generation (RAG).

Run Local LLMs and Build Practical AI Applications with Python

You’ll start by understanding the hardware and software requirements for running LLMs locally. Then you’ll install and configure the required tools, run your first local model, and verify that everything works on your computer.

From there, the course moves from setup into practical LLM application development. You’ll learn how LLM roles, tokens, context windows, prompts, and message flows work, and apply these concepts through Python-based examples.

You’ll also build practical capabilities including:

• Running open-source LLMs locally on Windows, macOS, and Linux
• Setting up a local AI development environment with Python and Poetry
• Connecting Python applications to local LLMs
• Understanding tokens, context windows, roles, and message flows
• Applying prompt engineering with practical coding examples
• Building multi-turn conversations with local LLMs
• Using tools and function calling to build an LLM-powered customer support agent
• Understanding Retrieval-Augmented Generation (RAG)
• Building a practical RAG application using a local LLM
• Working with concepts such as embeddings, vector databases, and retrieval
• Building privacy-focused AI applications that can operate locally

The course follows a hands-on, local-first approach. Instead of focusing primarily on LLM theory, you’ll learn by setting up the environment, running models, writing Python code, and building working LLM features.

This course is particularly useful if you want to understand local LLMs, offline AI, private AI, and Python-based LLM application development.

By the end of the course, you’ll have a working local LLM environment and the practical foundation required to build your own local AI applications.

A basic understanding of Python and the command line is recommended. No prior experience with LLMs or machine learning is required.

Who this course is for:

  • Developers and engineers who want to run powerful open-source LLMs locally without relying on cloud services, APIs, or subscriptions.
  • Python programmers looking to integrate language models into scripts, tools, or real-world applications in a fully offline environment.
  • Students or tech enthusiasts eager to explore AI and LLMs through a hands-on, practical course — without deep ML or data science background.
  • Makers, hackers, and open-source contributors who want full control over their AI tools and workflows with privacy and portability in mind.
  • Professionals in organizations exploring internal LLM applications for automation, chatbots, and document handling with no data leaving their system.
  • Anyone looking to quickly get up and running with LLMs, tools, prompt engineering, RAG, and chat-like experiences — all in a focused, crash-course format.

Report abuse