Qdrant 1.18 - TurboQuant - Qdrant
May 11, 2026Abdon Pijpelink

Summary
This post introduces TurboQuant, a new quantization method that offers twice the compression ratio of scalar quantization with similar recall and speed. It also details memory monitoring capabilities for collections, the ability to add/remove named vectors without recreating collections, improvements to audit logging (querying logs and request tracing IDs), per-collection API metrics, and new strict mode guardrails for memory and search batch size.
More from the CPU Performance for Vector Search trail
- Qdrant 1.19 - TurboQuant Datatype & Memory Tiers - Qdrant
- Qdrant Beats Elastic’s DiskBBQ at 2x Throughput, Half the Latency, and 1/3 the Compute - Qdrant
- Qdrant 1.15 - Smarter Quantization & better Text Filtering - Qdrant
- Intel’s New CPU Powers Faster Vector Search - Qdrant
- Qdrant Updated Benchmarks 2024 - Qdrant