SOURCE-LINKED INTELLIGENCE

Where Post-Training Quantization Breaks Text Embedders: A Measured Map Across Four Embedder Families

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Weight-only post-training quantization is the cheapest way to shrink a retrieval embedder, and the received advice for applying it -- protect the embedding table, allocate bits by module sensitivity, prefer a ranking-aware objective over weight reconstruction -- was carried into LLM quantization largely intact. We test that advice on retrieval embedders directly, quantizing five checkpoints from four architecture families across a grid of bit widths and group sizes, and isolating the embedding, attention and feed-forward blocks at each width. Every heuristic fails to transfer as stated. The em

Read original source ↗ Open in workspace

recordType

paper

region

Global