SOURCE-LINKED INTELLIGENCE

SPHQuant: Efficient extreme low bit weight quantization for Vision-Language Models

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Recent foundation models are moving toward native multimodal Vision-Language Models (VLMs), making VLMs a central form of next-generation foundation models. However, their large language backbones make edge deployment difficult due to high memory footprint and memory-bound autoregressive decoding. Weight-only post-training quantization is a practical solution, but pushing VLMs to extreme low bit-widths remains challenging: existing rotation-free methods suffer from outliers at 2-3 bits, while rotation-based methods improve accuracy at the cost of additional runtime overhead. We propose SPHQuan

Read original source ↗ Open in workspace

recordType

paper

region

Global