Running the Notebooks¶
The chapter notebooks use Qwen3:14B as the default model via Ollama.
Minimum hardware: ~16 GB RAM with a dedicated GPU. You can swap in a smaller
model (e.g. qwen3:4b), but smaller models may not follow tool-use
instructions reliably — especially in later chapters.
Option A — Run Locally¶
Install Ollama and pull the model:
Then launch Jupyter from the project root:
Option B — Lightning AI (Free)¶
No GPU? Lightning AI offers ~22 free GPU compute hours/month — enough for several sessions on an L4.
- Create a free account if you don't have one
- Open the book template
- Click Clone and ensure it's the latest version
- Launch the Studio with an L4 GPU
- Open any chapter notebook — Ollama and the model are pre-configured