landing_page/qdrant-landing/content/quantization/features.md

features, sitemapExclude

features

sitemapExclude

id icon title description image link 0 src alt /icons/outline/square-plus-teal.svg Plus Multi-Vector vs. Single-Vector Collections If your collection uses multi-vector representations for late-interaction retrieval, quantization delivers less memory relief than it does for single-vector collections. If you are sizing a multi-vector collection and wondering whether quantization changes the math, <a href="/contact-us/">contact us</a> and we will work through the numbers with you. src mobileSrc alt /img/quantization/folder.png /img/quantization/folder-mobile.png Plus url text /course/multi-vector-search/module-3/quantization-techniques/ Learn Quantization Techniques id icon title description link 1 src alt /icons/outline/circuit-board-teal.svg Circuit board Embedding Fit Some embedding models compress more cleanly than others, and the gap in recall varies by model. Check how your embedding model behaves under each quantization method before you size the cluster or commit to a configuration. url text /documentation/manage-data/quantization/ Check Embedding Compatibility id icon title description link 2 src alt /icons/outline/hard-drive-teal.svg Hard drive Storage Modes Keep your quantized vectors in RAM for fast lookups and let the full-precision originals live on disk. The memory setting lets you tune exactly which data stays hot and which moves to slower storage. url text /documentation/manage-data/quantization/ Configure Storage Modes

true