Build garageTry it → read → next · ~10 min

Tutorials · Chapter D (4/4) · ~10 min

Local model lab

Try it → see it → read → next

Run **Ollama or open weights** on your machine when privacy, cost, or offline matters.

On paths: Builder · Student

Try tools: Open source & local

Try yourself

Playground

Local model lab

Local/open weights for privacy and offline — cloud for capability and scale.

HR docs — cannot leave VPC

Recap

What you just did

You matched workloads to local vs cloud inference.

Read

Sketch

import ollama
out = ollama.chat(model="llama3.2", messages=[{"role": "user", "content": prompt}])