AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression

Minjun Kim, Jaehyeon Choi, Hyunwoo Yang, Jongjin Kim, Jinho Song, U Kang

ICLR 2026 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply stronger compression after weaker (quantize first, then prune) as the CER gap growsSparseGPT + QuaRot · WikiText-2 (LLaMA 2 7B/13B, LLaMA 3 8B)compression order advantageImproved
applying the progressive-intensity ordering to vision models (pruning + quantization)ResNet-18 and DeiT-Base · ImageNetaccuracyImproved
apply stronger pruning later in multi-stage compressionSparseGPT + QuaRot · WikiText-2 (LLaMA 3 8B)perplexityImproved
progressive (8 to 2 bit) instead of regressive bit allocation in mixed-precision quantizationHAWQ-V2 · ImageNet (ResNet-18)accuracyImproved
order of pruning and parameter sharingBasis Sharing + magnitude pruning · LLaMA 2 7BperplexityImproved
add Hadamard rotation before SparseGPT pruning (ablation)SparseGPT · WikiText-2 (LLaMA 3 8B, ratio 0.4)perplexity: 8.477 -> 98.213Hurt
add Hadamard rotation before SLEB pruning (ablation)SLEB · WikiText-2 (LLaMA 3 8B, ratio 0.4)perplexity: 92.848 -> 93.260No clear effect
unstructured (SparseGPT) vs structured (SLEB) pruning in order interference at 4-bitSparseGPT, SLEB · WikiText-2 (LLaMA 3 8B)order advantage: -49.899 vs -9.379Mixed
add post-quantization LoRASparseGPT + RTN · LLaMA 3 8BperplexityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy