Privacy-first professionals
You handle sensitive text, documents, or images and can’t justify sending them to cloud AI tools. This course shows you a practical way to keep your data on your own machine.
Local LLMs via Ollama & LM Studio - The Practical Guide
Learn how to run open large language models like Gemma, Llama or DeepSeek locally to perform AI inference on consumer hardware.
Course Overview
About This Course
You already use ChatGPT or Gemini—but the moment privacy, cost, offline access, or customization matters, the usual cloud chatbots start to feel like the wrong tool. You want AI that works on your terms, without sending prompts or documents to someone else’s servers.
In this course, you’ll get a guided, step-by-step path to running highly capable open models on your own machine. You’ll see what’s realistic on normal laptops vs. high-end PCs, and you’ll practice with approachable tools that remove the “too technical” barrier while still giving you real control.
By the end, you’ll be able to choose a model that fits your hardware and task, run it locally with confidence, and use it for real work—like analyzing documents and images—while keeping your data on-device. You’ll also be ready to plug your local AI into your own scripts or apps when you want more than a chat window.
What You'll Learn
You’ll go from picking an open model to running it locally with Ollama and LM Studio, then applying it to text, PDFs, and images—and finally wiring it into your own programs via built-in APIs.
Open-LLM use cases
Identify where local, open models beat cloud chatbots—especially when privacy, offline access, cost control, or deep customization is the deciding factor for your workflow.
Model selection skills
Choose and run specific open models such as Gemma 3, Llama 4, and DeepSeek, matching capability and speed to what you’re trying to accomplish on your own computer.
Hardware requirements clarity
Estimate what you can realistically run on your machine, including understanding the practical impact of having at least 8 GB of (V)RAM when you want to run models locally.
Quantization decisions
Use quantization as a practical lever to make large models feasible on consumer hardware, so you can trade off quality, speed, and memory usage intentionally instead of guessing.
Local runtime workflows
Install, configure, download, and run models in LM Studio, and interact with models through Ollama—so you can reliably operate local AI without depending on third-party chatbots.
API-based integration
Connect locally running models to your own scripts and applications using the built-in APIs provided by LM Studio and Ollama, enabling private AI features inside your tools.
Ready to get started?
See enrollment optionsPrerequisites
Basic understanding of LLM functionality and how to use AI chatbots.
No programming or advanced technical expertise is required.
If you want to run models locally, plan for at least 8 GB of (V)RAM.
Who Is This Course For?
Developers and builders
You want private AI inside your workflows or applications, not just another chatbot tab. You’ll leave knowing how to run local models and connect them to your own software when you’re ready.
AI power users
You already use AI tools and feel limited by subscriptions, internet dependence, or vendor lock-in. This is the next step if you want more control without needing deep technical expertise.
Curriculum Overview
Start NowPreview the structure and pacing of this course before you begin.
Course Introduction35m
- 01Welcome To The Course!2:06 min
- 02What Exactly Are "Open LLMs"?6:27 min
- 03Why Would You Want To Run Open LLMs Locally?6:52 min
- 04Popular Open LLMs - Some Examples3:43 min
- 05Where To Find Open LLMs?4:47 min
- 06Running LLMs Locally - Available Options7:17 min
- 07Check The Model Licenses!4:04 min
Understanding Hardware Requirements & Quantization23m
- 01LLM Hardware Requirements - First Steps4:21 min
- 02Module Introduction1:20 min
- 03Deriving Hardware Requirements From Model Parameters5:34 min
- 04Quantization To The Rescue!6:50 min
- 05Does It Run On Your Machine?5:50 min
LM Studio Deep Dive1h 35m
- 01Running Locally vs Remotely1:08 min
- 02Module Introduction2:03 min
- 03Installing & Using LM Studio3:09 min
- 04Finding, Downloading & Activating Open LLMs9:04 min
- 05Using the LM Studio Chat Interface4:53 min
- 06Working with System Prompts & Presets3:26 min
- 07Managing Chats2:32 min
- 08Power User Features For Managing Models & Chats6:28 min
- 09Leveraging Multimodal Models & Extracting Content From Images (OCR)2:48 min
- 10Analyzing & Summarizing PDF Documents3:27 min
- 11Onwards To More Advanced Settings1:52 min
- 12Understanding Temperature, top_k & top_p6:32 min
- 13Controlling Temperature, top_k & top_p in LM Studio4:45 min
- 14Managing the Underlying Runtime & Hardware Configuration4:17 min
- 15Managing Context Length5:21 min
- 16Using Flash Attention5:08 min
- 17Working With Structured Outputs5:29 min
- 18Using Local LLMs For Code Generation2:35 min
- 19Content Generation & Few Shot Prompting (Prompt Engineering)5:21 min
- 20Onwards To Programmatic Use2:25 min
- 21LM Studio & Its OpenAI Compatibility6:00 min
- 22More Code Examples!5:04 min
- 23Diving Deeper Into The LM Studio APIs2:10 min
- 24Using the Python / JavaScript SDKs0:00 min
Ollama Deep Dive1h 16m
- 01Installing & Starting Ollama2:08 min
- 02Module Introduction1:41 min
- 03Finding Usable Open Models2:56 min
- 04Running Open LLMs Locally via Ollama7:43 min
- 05Adding a GUI with Open WebUI2:12 min
- 06Dealing with Multiline Messages & Image Input (Multimodality)2:38 min
- 07Inspecting Models & Extracting Model Information3:31 min
- 08Editing System Messages & Model Parameters6:01 min
- 09Saving & Loading Sessions and Models3:35 min
- 10Managing Models5:42 min
- 11Creating Model Blueprints via Modelfiles6:22 min
- 12Creating Models From Modelfiles3:26 min
- 13Making Sense of Model Templates6:39 min
- 14Building a Model From Scratch From a GGUF File6:37 min
- 15Getting Started with the Ollama Server (API)2:12 min
- 16Exploring the Ollama API & Programmatic Model Access5:18 min
- 17Getting Structured Output2:56 min
- 18More Code Examples!4:53 min
- 19Using the Python / JavaScript SDKs0:00 min
Course Roundup1m
- 01Roundup1:44 min
Ready to Get Started?
Choose the option that works best for you.
Single Course
Local LLMs via Ollama & LM Studio - The Practical Guide
One Payment. Lifetime Access.
$69one-time
- One-time payment
- All future updates for this course
- Downloadable resources & code
- Certificate of completion
- Hands-on exercises & projects
- Self-paced learning
- English captions on all videos
- Lifetime access
Most Popular
All-Access Membership
Everything we teach. One subscription.
$25/mo
$4,729+ worth of courses
- Full access to all courses
- All future courses included
- Downloadable resources & code
- Certificates of completion
- Hands-on exercises & projects
- Self-paced learning
- English captions on all videos
- Cancel anytime