AIWeaviate 1.39 adds 4-bit Rotational Quantization
Weaviate says the new 4-bit option cuts memory use while maintaining strong recall, alongside faster imports and search improvements across the RQ family.
TLDR
Weaviate announced 4-bit Rotational Quantization (RQ) in version 1.39 for users prioritizing lower RAM use and cost. The company claims reduced memory use while maintaining strong recall, plus faster imports and search improvements across the RQ family. It says 8-bit RQ remains the default in Weaviate Cloud and now imports 16% faster.
Combined views
1.8K
3 Sources, first seen 12h ago
likes
Weaviate 1.39 adds 4-bit Rotational Quantization
Weaviate says the new 4-bit option cuts memory use while maintaining strong recall, alongside faster imports and search improvements across the RQ family.