Generate 100 paid-social ad variants per hour on a local M-series Mac via Ollama + Llama 3.3 70B, then run a second pass that scores each variant 0-100 on hook, value clarity, and CTA specificity. The full prompt pair, the Python wrapper, and the math that makes $0 marginal cost win over GPT-4o at any team size.
A 30-day blind test: 800 meta titles + 800 product descriptions rewritten by both Qwen 2.5 14B (self-hosted on a refurbished workstation) and Claude Sonnet 4, rated by 3 SEO contractors. The result is not a clean win for open weights — it's a split. Where Qwen breaks even, where it collapses, and the actual cost math behind self-hosting for repeat-pattern SEO work.
