---
id: "nr-weaviate-1-39-adds-4-bit-rotational-quantization-for-f80d29"
slug: "weaviate-1-39-adds-4-bit-rotational-quantization-for-f80d29"
title: "Weaviate 1.39 adds 4-bit Rotational Quantization for vector storage"
observed_at: "2026-09-18T13:48:49+00:00"
record_date: "2026-09-18"
date_kind: "observed_at"
novelty: "new"
source_platform: "x.com"
topics: ["vector-databases","quantization","retrieval"]
entities: ["Weaviate"]
related_patterns: []
source_url: "https://x.com/weaviate_io/status/2100600774170399089"
source_urls: ["https://x.com/weaviate_io/status/2100600774170399089"]
basket: {"id":"0325e6b8-f527-4f9b-bfa3-3f30e57f380b","revision":1,"cluster_id":"f80d29cc-b659-4316-86db-8e854c9151f5"}
type: "raw_signal"
description: "Weaviate 1.39 introduces 4-bit Rotational Quantization to cut memory use while keeping strong recall, and speeds up 8-bit RQ imports by 16%."
why_it_matters: "For retrieval systems where RAM dominates cost, 4-bit RQ offers a lower-memory option at a possible recall cost, while the default stays at 8-bit. The post states no specific recall numbers, memory reduction ratio or dataset sizes, so the trade-off must be measured on each workload."
verification_level: "source-inspected"
signal_type: "newsroom_basket_signal"
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:weaviate-1-39-adds-4-bit-rotational-quantization-for-f80d29"
retrieval_nugget: "Weaviate 1.39 introduces 4-bit Rotational Quantization to cut memory use while keeping strong recall, and speeds up 8-bit RQ imports by 16%. Weaviate 1.39 adds 4-bit Rotational Quantization, which the company says cuts memory usage while maintaining strong recall, with faster imports and search improvements across the RQ family. 8-bit RQ remains the default in Weaviate Cloud and now imports"
status: "published"
visuals: []
routes: {"html":"https://newruntime.com/signals/weaviate-1-39-adds-4-bit-rotational-quantization-for-f80d29/","markdown":"https://newruntime.com/signals/weaviate-1-39-adds-4-bit-rotational-quantization-for-f80d29.md","json":"https://newruntime.com/signals/weaviate-1-39-adds-4-bit-rotational-quantization-for-f80d29.json"}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
---

# Weaviate 1.39 adds 4-bit Rotational Quantization for vector storage

## Retrieval answer

Weaviate 1.39 introduces 4-bit Rotational Quantization to cut memory use while keeping strong recall, and speeds up 8-bit RQ imports by 16%. Weaviate 1.39 adds 4-bit Rotational Quantization, which the company says cuts memory usage while maintaining strong recall, with faster imports and search improvements across the RQ family. 8-bit RQ remains the default in Weaviate Cloud and now imports

Weaviate 1.39 adds 4-bit Rotational Quantization, which the company says cuts memory usage while maintaining strong recall, with faster imports and search improvements across the RQ family. 8-bit RQ remains the default in Weaviate Cloud and now imports 16% faster. An accompanying blog covers the SIMD work, recall at scale and a comparison with TurboQuant.

For retrieval systems where RAM dominates cost, 4-bit RQ offers a lower-memory option at a possible recall cost, while the default stays at 8-bit. The post states no specific recall numbers, memory reduction ratio or dataset sizes, so the trade-off must be measured on each workload.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Vector Databases](https://newruntime.com/topics/vector-databases.md): Explore the vector-databases topic hub.
- topic hub: [Quantization](https://newruntime.com/topics/quantization.md): Explore the quantization topic hub.
- topic hub: [Retrieval](https://newruntime.com/topics/retrieval.md): Explore the retrieval topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)