---
title: "Match the optimization to the bottleneck"
description: "Choose an optimization for three different problems: weights that cannot fit, wasted cache reservations, and slow decoding."
canonical_url: "https://fanout.sh/ai-engineering/lessons/quantization-summary-pdf"
md_url: "https://fanout.sh/ai-engineering/lessons/quantization-summary-pdf.md"
access: "public"
---

# Match the optimization to the bottleneck

Choose an optimization for three different problems: weights that cannot fit, wasted cache reservations, and slow decoding.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md