# How BBQ shrinks Jina v5 embeddings by 29x without losing recall in Elasticsearch

DevFeed: [How BBQ shrinks Jina v5 embeddings by 29x without losing recall in Elasticsearch](<https://devfeed.tech/articles/how-bbq-shrinks-jina-v5-embeddings-by-29x-without-losing-recall-in-elasticsearch-78728.md>)

Original publisher: [Read original article](<https://www.elastic.co/search-labs/blog/bbq-quantization-jina-embeddings-v5>)

Author: Jeffrey Rengifo

Published: 2026-07-10T00:00:00Z

Content type: tutorial

Language: en

Sources: [Elasticsearch Labs](<https://devfeed.tech/sources/elasticsearch-labs.md>)

Topics: [elasticsearch](<https://devfeed.tech/topics/elasticsearch.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [vector embeddings in AI](<https://devfeed.tech/topics/vector-embeddings-in-ai.md>)

Tags: [000](<https://devfeed.tech/tags/000.md>), [elasticsearch](<https://devfeed.tech/tags/elasticsearch.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [jina-ai](<https://devfeed.tech/tags/jina-ai.md>), [ml-research](<https://devfeed.tech/tags/ml-research.md>), [v5](<https://devfeed.tech/tags/v5.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-database](<https://devfeed.tech/tags/vector-database.md>)

## AI overview

A hands-on Elasticsearch comparison tests Better Binary Quantization (BBQ) against float32 vector indices using Jina embeddings v5 on a multilingual news corpus. In this test, BBQ reduced the estimated in-memory vector footprint from 12.71 MB to 0.44 MB, while recall@10 was 0.994 at 1x oversampling. Disk usage was roughly similar, with the BBQ index slightly larger.

## Source excerpt

A hands-on test comparing BBQ and float32 vector indices in Elasticsearch, measuring memory, disk and recall@10 across five languages.