Gemma read the parking sign perfectly. Then it got the rule wrong.

Automated excerpt

A local open-weight model (Gemma 3 4B through Ollama) reads both photos. The model then writes the letter from facts you confirmed. Gemma 3 4B does both jobs that need a model: reading the ticket and sign photos (vision) and writing the letter.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.