Qdrant 1.20 cuts vector storage to 1/4 with turbo8, boosts nested filters 4x
qdrant_engine · x · 2026-11-05
Qdrant 1.20 makes search cheaper and faster: turbo8/turbo16 quantization stores vectors in 1/4 or 1/2 the space of float32 (100k 1536-dim vectors drop from 585MB to 293MB/147MB) with recall holding steady (94.8% → 95.0%/95.4%), and nested filters get up to 4x more queries per second.
Related event: Qdrant 1.20 Cuts Vector Storage Up to 75% and Speeds Nested Filtering 4x(2 posts)→
More from Infra
- US AI scale faces two physical gates: delivered power and manufacturing — ingliguori · 2026-11-05
- Liquid AI ships LFM 3 models (1.7B/2B) running locally on iPhone Duo via MLX — helloiamleonie · 2026-11-05
- Yuma backs Bittensor subnet Fugal claiming GPT-5.5-level results at 1/6 the cost — markjeffrey · 2026-11-05
- Speculative decoding makes Qwen3.6/3.8 much faster, latest draft model adds ~10% — teortaxesTex · 2026-11-05
- webAI open-sources 8.8B TwIL-8B hitting 93% of frontier coding performance — dr_cintas · 2026-11-05
- Together Compiler optimizes new open models for production in hours, not weeks — togethercompute · 2026-11-05