Local LLMs via Ollama & LM Studio - The Practical Guide
3h 52m 28s
English
Paid
Course description
AI assistants like ChatGPT and Google Gemini have become everyday tools. However, when privacy, cost, offline operation, or flexible customization are important, the best solution is to run powerful open language models (LLM) directly on your own computer.
In this course, you will learn how to run and use local AI models, such as Llama by Meta, Gemma by Google, and DeepSeek, even on a regular laptop—without clouds, subscriptions, or data leaks.
Read more about the course
Why Local and Open LLMs?
In a world dominated by cloud services, local LLMs offer a real advantage:
- No subscriptions - use powerful models for free
- 100% privacy - all data stays on your computer
- Offline capability - run AI in offline mode
- Freedom from vendors - access to a rapidly growing ecosystem of open-source models
- Cutting-edge capabilities - open models are among the top in global rankings!
What you will learn:
- Overview of open LLMs: where to find them, how to choose them, and why they are important
- Hardware requirements: what you need to run models locally
- Model quantization: how to run even "heavy" AI on a regular PC
- LM Studio: installation, setup, launch, and use of models
- Ollama: a convenient way to manage LLM from the terminal or API
- Practice: image processing, PDF document summaries, text generation, few-shot prompting, and more
- Integration into your own projects: working with APIs and automation
Who the course is for:
- Developers who want to integrate AI into applications
- Enthusiasts and students interested in cutting-edge technologies
- Those who value privacy and control over their data
- Anyone who wants to save on subscriptions and explore the capabilities of modern LLMs
Watch Online
0:00
/ #1: Welcome To The Course!
All Course Lessons (54)
| # | Lesson Title | Duration | Access |
|---|---|---|---|
| 1 | Welcome To The Course! Demo | 00:19 | |
| 2 | What Exactly Are "Open LLMs"? | 06:28 | |
| 3 | Why Would You Want To Run Open LLMs Locally? | 06:53 | |
| 4 | Popular Open LLMs - Some Examples | 03:44 | |
| 5 | Where To Find Open LLMs? | 04:48 | |
| 6 | Running LLMs Locally - Available Options | 07:18 | |
| 7 | Check The Model Licenses! | 04:05 | |
| 8 | Module Introduction | 01:21 | |
| 9 | LLM Hardware Requirements - First Steps | 04:22 | |
| 10 | Deriving Hardware Requirements From Model Parameters | 05:35 | |
| 11 | Quantization To The Rescue! | 06:51 | |
| 12 | Does It Run On Your Machine? | 05:51 | |
| 13 | Module Introduction | 02:04 | |
| 14 | Running Locally vs Remotely | 01:09 | |
| 15 | Installing & Using LM Studio | 03:10 | |
| 16 | Finding, Downloading & Activating Open LLMs | 09:05 | |
| 17 | Using the LM Studio Chat Interface | 04:54 | |
| 18 | Working with System Prompts & Presets | 03:27 | |
| 19 | Managing Chats | 02:33 | |
| 20 | Power User Features For Managing Models & Chats | 06:29 | |
| 21 | Leveraging Multimodal Models & Extracting Content From Images (OCR) | 02:49 | |
| 22 | Analyzing & Summarizing PDF Documents | 03:28 | |
| 23 | Onwards To More Advanced Settings | 01:53 | |
| 24 | Understanding Temperature, top_k & top_p | 06:33 | |
| 25 | Controlling Temperature, top_k & top_p in LM Studio | 04:46 | |
| 26 | Managing the Underlying Runtime & Hardware Configuration | 04:18 | |
| 27 | Managing Context Length | 05:22 | |
| 28 | Using Flash Attention | 05:09 | |
| 29 | Working With Structured Outputs | 05:30 | |
| 30 | Using Local LLMs For Code Generation | 02:36 | |
| 31 | Content Generation & Few Shot Prompting (Prompt Engineering) | 05:22 | |
| 32 | Onwards To Programmatic Use | 02:26 | |
| 33 | LM Studio & Its OpenAI Compatibility | 06:01 | |
| 34 | More Code Examples! | 05:05 | |
| 35 | Diving Deeper Into The LM Studio APIs | 02:11 | |
| 36 | Module Introduction | 01:42 | |
| 37 | Installing & Starting Ollama | 02:09 | |
| 38 | Finding Usable Open Models | 02:57 | |
| 39 | Running Open LLMs Locally via Ollama | 07:44 | |
| 40 | Adding a GUI with Open WebUI | 02:13 | |
| 41 | Dealing with Multiline Messages & Image Input (Multimodality) | 02:39 | |
| 42 | Inspecting Models & Extracting Model Information | 03:32 | |
| 43 | Editing System Messages & Model Parameters | 06:02 | |
| 44 | Saving & Loading Sessions and Models | 03:36 | |
| 45 | Managing Models | 05:43 | |
| 46 | Creating Model Blueprints via Modelfiles | 06:23 | |
| 47 | Creating Models From Modelfiles | 03:27 | |
| 48 | Making Sense of Model Templates | 06:40 | |
| 49 | Building a Model From Scratch From a GGUF File | 06:38 | |
| 50 | Getting Started with the Ollama Server (API) | 02:13 | |
| 51 | Exploring the Ollama API & Programmatic Model Access | 05:19 | |
| 52 | Getting Structured Output | 02:57 | |
| 53 | More Code Examples! | 04:54 | |
| 54 | Roundup | 01:45 |
Unlock unlimited learning
Get instant access to all 53 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.
Learn more about subscriptionComments
0 commentsWant to join the conversation?
Sign in to commentSimilar courses
Turbo Mode: Optimizing Productivity with AI Tools and Agents
Sources: vueschool.io, Justin Schroeder, Daniel Kelly, Garrison Snelling
Find out how to create custom AI agents and develop universal rules to enhance your productivity and address all aspects of the project.
1 hour 2 minutes 46 seconds
Build a Reasoning Model (From Scratch)
Sources: Sebastian Raschka
Understand how LLMs reason by creating your own reasoning model from scratch. In the book "Building a Reasoning Model from Scratch," you will step by step...
3D Browser Game Development with AI and Cursor
Sources: Kevin Kern (instructa.ai)
Hello everyone! Welcome to the course "Development of a 3D Browser Game with AI and Cursor". I'm glad to see you here! First, I want to tell you why we...
2 hours 7 minutes 55 seconds
AI Engineering Bootcamp: Building AI Applications (LangChain, LLM APIs + more)
Sources: zerotomastery.io
This course is your practical path to a career as a generative AI engineer: not just using technologies, but creating them. First, you will enhance your skills.
18 hours 33 minutes 41 seconds