30 minutes · Medium

Build a Small Local AI Workbench

Leave with one local model test, one hosted comparison, and a tiny eval you can rerun.

This rabbit hole keeps the AI experiment small: one local baseline, one hosted comparison, and one repeatable check.

1. Start with a small local model

   Use Ollama Library to choose a model that your machine can run comfortably.

   Ollama Library

2. Compare against hosted models

   Use OpenRouter Models to compare context, price signals, and provider availability.

   OpenRouter Models

3. Turn one prompt into a test

   Use promptfoo to capture three inputs and one behavior expectation before changing models.

   promptfoo