From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization

arXiv:2604.19884v1 Announce Type: cross Abstract: Post-Training Quantization (PTQ) is critical for the efficient deployment of Large Language Models (LLMs). While 4-bit quantization is widely regarded as an optimal trade-off, reducing the precision to 2-bit usually triggers a catastrophic...