Getting Started with Ollama
Published by O'Reilly Media, Inc.
Running and using local LLMs
Course outcomes
- Run and manage local LLMs using Ollama CLI commands
- Compare and select free local models based on task, size, and system constraints
- Create and execute a customized Ollama model using a Modelfile
- Integrate Ollama into a simple application using the local REST API
Course description
If you’re new to Ollama, Brent Laster introduces it as a practical way to run open models locally for development, experimentation, and lightweight AI application prototyping. Ollama provides CLI commands, model management, Modelfiles, and a local HTTP API for working with LLMs.
You’ll understand how Ollama fits into the local AI tooling landscape, how to install and run models, how to manage models from the command line, and how to interact with Ollama from scripts and applications through its local API. And you’ll run your first local model, create a simple customized model with a Modelfile, and call Ollama from a small Python application.
This live event is for you because...
- You’re a developer, architect, DevOps engineer, data practitioner, or AI-curious technical professional.
- You want to run LLMs locally without requiring paid API keys.
- You need a practical introduction to local model execution for prototyping, demos, labs, RAG experiments, or agent workflows.
- You want to understand where Ollama fits before adopting larger AI frameworks.
Prerequisites
- A GitHub user ID on the public GitHub.com site (free tier is fine)
- Basic command-line familiarity
- Basic understanding of what an LLM is
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
What Ollama is and why it matters (20 minutes)
- Presentation: Local LLMs and Ollama’s role; what Ollama does; why local models matter—privacy, no per-call API cost, offline experimentation, repeatable training environments; where Ollama fits compared with cloud APIs, LM Studio, llama.cpp, Docker-based serving, and hosted inference; common use cases; prompt experimentation; coding assistant backends; RAG prototypes; agent tool demos offline or privacy-sensitive labs; core Ollama concepts
- Group discussion: Where would a local model be useful in your work, and where would a hosted model still make more sense?
- Q&A
First model run and CLI basics (25 minutes)
- Presentation: Core Ollama commands and their function; use cases
- Hands-on exercise: Pull and run a free local model and inspect what is installed
- Q&A
- Break
Choosing models and controlling behavior (30 minutes)
- Presentation: Choosing a model by task; practical model-selection criteria; why model behavior needs control; what a Modelfile is; common Modelfile instructions
- Hands-on exercise: Create a lightweight customized model definition with system instructions and parameters
- Q&A
Using Ollama from applications (30 minutes)
- Presentation: Ollama’s locally available service; why the API matters; key API concepts; CLI for experimentation, API for automation, and Python/JavaScript libraries for applications; practical cautions
- Hands-on exercise: Use Ollama from a simple Python script through the local API
- Q&A
Troubleshooting and next steps (10 minutes)
- Presentation: Common issues; basic troubleshooting commands; suggested next steps
- Q&A
Your Instructor
Brent Laster
Brent Laster is an experienced technology leader and a global trainer, speaker and author. He’s also the founder and president of Tech Skills Transformations, LLC, a company dedicated to making technology understandable and usable. Throughout his career in software development and management, Brent has always made time to learn and develop both technical and leadership skills and share them with others. He believes that regardless of the topic or technology, there’s no substitute for the excitement and sense of potential that come from providing others with the knowledge they need to accomplish their goals.