How do I pull and run your first model?

# Download and Launch a Model Browse models at [https://ollama.com/library](https://ollama.com/library). Start with `gemma3` or `llama3.2`. Pull and run interactively: ```bash ollama run gemma3 ``` This downloads the model (~4-8GB depending on size) and opens a chat prompt. Type questions like "Explain neural networks" and press Enter. List local models: `ollama list`. Exit with `/bye`.

How do I explore cli and model management?

# Master CLI Commands Run Ollama service: `ollama serve` (runs in background). Key commands: - `ollama pull `: Download only. - `ollama run `: Pull if needed and chat. - `ollama show `: Inspect model info. - `ollama rm `: Remove model. - `ollama ps`: Running models. Create custom Modelfile for fine-tuning (docs: [GitHub Modelfile](https://github.com/ollama/ollama/blob/main/docs/modelfile.md)). Example: Create simple Modelfile and build.

How do I use the rest api?

# Interact via HTTP API Ollama exposes API at http://localhost:11434. Test chat: ```bash curl http://localhost:11434/api/chat -d '{"model": "gemma3", "messages": [{"role": "user", "content": "Why is the sky blue?"}], "stream": false}' ``` Endpoints: /api/generate, /api/chat, /api/tags (list models). Full docs: [https://github.com/ollama/ollama/blob/main/docs/api.md](https://github.com/ollama/ollama/blob/main/docs/api.md). Use tools like Postman or curl for testing.

How do I integrate with python and build an app?

# Python Library Hands-On Install: `pip install ollama` Simple chat script: ```python from ollama import chat response = chat(model='gemma3', messages=[{'role': 'user', 'content': 'Hello!'}]) print(response['message']['content']) ``` Stream responses and build a loop for interactive chat. Explore JS library similarly: `npm i ollama`. Next: Integrate with Streamlit or Flask for web app (repo examples: [https://github.com/ollama/ollama-python](https://github.com/ollama/ollama-python)).

Learn Ollama: Run LLMs Locally in 5 Steps

Q: How do I install ollama?

# Install Ollama on Your System Ollama supports macOS, Linux, and Windows. Follow the platform-specific instructions: ## macOS or Linux ```bash curl -fsSL https://ollama.com/install.sh | sh ``` ## Windows (PowerShell) ```powershell irm https://ollama.com/install.ps1 | iex ``` Alternatively, download installers from [https://ollama.com/download](https://ollama.com/download). After installation, verify by running `ollama --version` in your terminal. Ollama runs as a service on port 11434.

🧰

Instant Toolkit

2 artifacts

📋
Step-by-Step Guide

1

Install Ollama on Your System

Ollama supports macOS, Linux, and Windows. Follow the platform-specific instructions:

macOS or Linux

curl -fsSL https://ollama.com/install.sh | sh

Windows (PowerShell)

irm https://ollama.com/install.ps1 | iex

Alternatively, download installers from https://ollama.com/download.

After installation, verify by running ollama --version in your terminal. Ollama runs as a service on port 11434.

Why this step matters:

-Establishes the foundation for local LLM execution without cloud dependency
-Enables privacy-focused AI workflows on your hardware

15-30 minutes

Terminal/PowerShell, curl (Linux/macOS), Web browser

$0

Definition of Done

•Ollama installed successfully
•`ollama --version` shows version (e.g., 0.3.17+)

Common Mistakes to Avoid

❌ Firewall or antivirus blocks installation script

→Temporarily disable or allow ollama.com domains

❌ Missing prerequisites like curl on Windows

→Download installer .exe instead of PowerShell script

2

Following along, or just reading? 👀

Spin up a personalized “learn Ollama” plan you can save, check off, and return to anytime — unlimited on the free trial.

Start free trial →

3

4

5

🎥
Suggested Videos

Learn Ollama in 15 Minutes - Run LLM Models Locally

Ollama Course – Build AI Apps Locally

📚
Learning Resources

📖 Online Courses

Zero to Hero in Ollama: Create Local LLM Applications

beginner

Paid

Udemy

Harnessing Ollama – Create Local LLMs with Python

beginner

Paid

Coursera

🌐 Helpful Websites

Ollama Official GitHub

documentation

README, docs, Modelfile, API reference

Ollama Library

documentation

Browse and discover models

Ollama Download

documentation

Installers and scripts for all platforms

🛠️ Useful Tools

Ollama CLI

AI Runtime

Core command-line tool for running models

ollama-python

SDK

Official Python client library

Learn Ollama: Run LLMs Locally in 5 Steps