landing_page/qdrant-landing/content/quantization/faq.md at master

krzysztof/landing_page

Fork 0

mirror of https://github.com/qdrant/landing_page.git synced 2026-09-26 14:38:30 +02:00

Files

T

141e6439f8 Add quantization page (#2694 )

* add quantization page

* link fix

* small content fixes

* Restore used texture.png; remove unused chart-background-texture.png

texture.png is referenced by _configuration.scss (desktop banner overlay3)
and was deleted by mistake. chart-background-texture.png is unreferenced
anywhere in the source, so remove that one instead.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: trean <trean.mi@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

2026-09-04 18:33:53 +02:00

843 B

Raw Permalink Blame History

title, questions, sitemapExclude

title

questions

sitemapExclude

FAQs

question	answer
Does quantization require a paid tier?	No. Quantization is available across Qdrant deployment modes and is not gated behind a paid tier. Enable it on Qdrant Cloud, Hybrid Cloud, Private Cloud, Edge, or self-hosted.

question	answer
Will I lose recall when I turn quantization on?	Compression does reduce recall if you search the quantized index alone. Enable rescoring on your search requests so Qdrant re-ranks candidates against the original vectors and recovers most of the accuracy.

question	answer
Which quantization method should I start with?	The comparison matrix in the docs shows memory savings, recall, and speed for scalar, product, and binary quantization side by side. Review it against your embedding model and latency budget before you pick.

true

843 B Raw Permalink Blame History

843 B

Raw Permalink Blame History