🧠

Models Track

Understand how LLMs work, run models locally, and benchmark their performance across different tasks.

Sections 2

Prerequisites Python, API basics

Background Reading

For a deeper understanding of the transformer architecture that powers modern LLMs:

Install Ollama, pull a model that runs on your laptop, and write a small agent using your local model

Write a benchmark for your agent (consistent scoring mechanism to determine quality of the run)

Run your agent with each model: GPT-5, 4.1-mini, 4.1-turbo, o3, Claude 3.5, 3.7, 4, 4.5 and your local Ollama model

← Back to Home Agent Track →