Want to start learning LLM and Generative AI? Start with Ollama and this article.

Generative AI and Large Language Models (LLMs) are the buzzwords redefining how we create, automate, and interact with technology. From chatbots that sound almost human to tools that can generate lines of code or full-fledged content in seconds, the potential is limitless.

However, getting started with LLMs can feel overwhelming. The complexity of models, infrastructure, and jargon can make even seasoned developers pause. You must have asked, "Where should I start?”.

That’s where Ollama comes in. If you’re a developer who wants to experiment with Generative AI without getting lost in the setup maze or spending a fortune on cloud services, Ollama is the perfect starting point. It’s simple, powerful, and respects your time and privacy.

What is Ollama?

Ollama allows you to run and manage large language models locally. Yes, locally. That means no cloud dependency, no massive data transfers, and no recurring bills for cloud computing power.

1. Choose Your Language Model: Whether you want to explore conversational AI, code generation, or content creation, Ollama lets you pick from various models. No need to jump between platforms; everything you need is here.

1. Fast and Cost-Effective: Run models directly on your computer without relying on cloud services. That means no extra expenses for computing power and faster response times — perfect for beginners experimenting on a budget.

2. Start Small, Learn Big: Ollama is built for all skill levels. Whether you’re just starting with AI or looking to expand your toolkit, the platform provides an easy entry point into LLMs with a clear path to more advanced capabilities. The installation is an easy-breezy process. You may check out the quick installation guide here in the next section.

3. Hands-On Experimentation: Experiment locally without worrying about setting up complicated infrastructure. Download a model, start playing, and learn as you go — no need for a big upfront commitment.

How to install Ollama and get started?

Here’s how you can setup Ollama locally and start running the language models:

1. Head over to Ollama to download the installer for your OS.

1. After that is installed locally, bring up a terminal and run the following:

ollama run llama3.2

… or any model of your choice.

You are expected to see it downloading the models (if that’s your first time running the model), and once it is done, you will see a prompt:

You are set to go! You can experiment with various models (but please take note that the model images are pretty large).

That’s it for today’s article! If you are planning to get started with your Gen AI / LLM journey, do follow me on Medium (it’s been some time since I last posted, but I will dedicate myself to posting every week again with very useful technical blogs on AI).
Cheers!