Open, local, free, closed, hosted, and paid AI are often discussed together, but they do not all mean the same thing. In this module, you’ll learn the key distinctions that help you understand what kind of AI tool or model you are actually using. You’ll explore why open-weight models can give you more flexibility, why “free” can mean different things, and why hosted closed models are still useful for many tasks. By the end of the module, you’ll be able to explain the basic tradeoffs around cost, privacy, convenience, control, and quality, and you’ll be better prepared to recognize when local AI might be a good fit.

You’ll learn how to choose models more thoughtfully. In this module, you’ll use LM Studio as a workspace for exploring, comparing, downloading, and testing open-weight models on your own computer. You’ll learn how to read beginner-friendly model details like parameter count, file size, quantization, context length, license, and memory fit. You’ll also practice judging whether a model fits both your task and your hardware. By the end of the module, you’ll understand why the biggest model is not always the best model, and how to choose a local model that runs comfortably and gives useful results.

Local AI becomes more powerful when it moves beyond a single chat window. In this module, you’ll use LM Studio’s local server to connect a local model to a simple application through an API. You’ll build or follow a local AI-powered fitness plan workflow that reads sample client documents and generates first-draft weekly plans for review. Along the way, you’ll see how open, local AI can support repeated work while giving you more control over cost, data processing, and customization. By the end of the module, you’ll understand how a local model can become part of a practical app or agent-style workflow.

In this final module, you’ll step back and turn what you learned into a practical decision-making framework. Instead of trying to use one AI approach for everything, you’ll reflect on which option fits which situation. You’ll consider when hosted AI may be the best choice, when local AI is worth using, when open-weight models are useful, when closed tools may be more convenient, and when a hybrid workflow makes the most sense. By the end of the module, you’ll have a simple personal AI strategy you can use for your own work, learning, or projects.