method · first seen 4 Oct 2026
post-training quantization
Also: AWQ, PTQ, NF4 quantization, full integer quantization
Compressing a trained neural network to lower bit-widths without retraining or access to training data.
Post-training quantization compresses an already trained network to lower bit-widths (int8, int4, FP4 and below) using at most a small calibration set, with no retraining. The sources are a steady stream of incremental arXiv work rather than a new idea: a framework for looped language models, a study of weight averaging during pretraining and its effect on PTQ, Huawei's MACaQ (an MXFP4 W4A4 method released with code), work on calibration data for sub-4-bit models, measurement-noise studies, and edge deployment papers built on GPTQ and AWQ formats. Applications now extend to vision-language-action policies and robot world models.
PTQ is already a standard step for deploying large models. The newer work matters mainly for 4-bit-and-below weight-activation formats such as MXFP4 and for checking whether quantized models keep their robustness, not just their headline accuracy.
Analyst note (established), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 126 on 14 Nov 2026 · 46 mentions in 28 days · 46 independent groups · papers → code · first seen 6 weeks ago · acceleration +0.24
Earliest sources
- Loopy: Low-Bit Quantization Framework for Looped Language ModelsPapers · 4 Oct 2026 · Zeyu Li, Yipu Zhang, Jintao Cheng, Xin Li, Wei Zhnag
- Understanding the Weight Averaging Mechanism in LLM Training for Post-Training QuantizationPapers · 4 Oct 2026 · Hanzhang Wang, Tianqi Shen, Zonglin Liu, Junze He, Difan Zou, Ziye Ma
- Offline AI Modules: Voice-First Offline Architecture, Hardware Reference Stack, Quantization and BenchmarkingPapers · 4 Oct 2026 · Sunday Afariogun, Odunolaoluwa Jenrola, Zeinab Nezami
- Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented TuningPapers · 5 Oct 2026 · Shen Ruan, Wenchang Gao, Jin Wang, Siao Liu, Zhaxizhuoma, Dongchun Ren, Xin Zhen…
- SoloQ: Calibration-Free Quantization for Diffusion Language ModelsPapers · 5 Oct 2026 · Donghyun Lee, Arkapravo Ghosh, Varun Manjunath, Bumjoon Kyle Rhee, Hyunho Kook,…
- AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM GenerationPapers · 5 Oct 2026 · Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe Fen…
Latest sources
- JointQ: Joint Scale-and-Integer Quantization for Large Language ModelsPapers · 16 Nov 2026 · Keiji Kimura, Yuma Ichikawa
- LazyWeights: Decode-on-Demand Edge LLMsPapers · 12 Nov 2026 · Arnab Sanyal, Gourav Datta, Sandeep P. Chinchali
- The Noise Floor of a Quantization Comparison: Engine, restart, batch and kernel drift, measured against 8-bit and 4-bit effects in two decision modelsPapers · 11 Nov 2026 · Aleks Blagojevich, Trevor Sunderland
- Edge-Native Multimodal RAG: Hardware-Aware Quantization and Architectural Optimization for Consumer GPUsPapers · 11 Nov 2026 · Zahraa Selim, Menna Hamed, Wesam Ahmed, Sohyla Said, Sara Basheer, Rami Zewail
- huawei-csl/MACaQCode · 10 Nov 2026 · huawei-csl · 353 stars
- How Far Does Second-Order Linear Response Predict Quantization Mismatch? Pre-Registered Measurements on Five Language ModelsPapers · 9 Nov 2026 · Dezhen Lu, Zixiang Ni
- AutoQS: Automated Quantization Strategy Design with Large Language ModelsPapers · 9 Nov 2026 · Zhen Liu, Zhiqin Yang, Yonggang Zhang, Jianyi Liu, Jinjun Wang, Jingwen Fu
- Planners Exploit Deterministic Error: Dithered Low-Bit World ModelsPapers · 9 Nov 2026 · Yong Hwi Song, Keon Myung Lee
- When Calibration Data Matter in Sub-4-Bit Language Model QuantizationPapers · 8 Nov 2026 · Yehong Jiang, Yen-Kuang Chen, Xinmin Tian
- MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and ActivationsPapers · 7 Nov 2026 · Lorenz K. Muller, Philippe Bich, Chiara Boretti, Hyun-Min Chang, Jiawei Zhuang,…
- CucumberVision at the Edge: Accuracy, Throughput, and Energy of RGB-D Cucumber Sizing on Jetson Orin Nano and Raspberry Pi 4Papers · 6 Nov 2026 · Manveen Kaur, Rajmeet Singh, Saeed Mozaffari, Majid Ahmadi, Shahpour Alirezaee
- Enabling Retraining-Free Accurate Inference in Analog Compute in Memory AcceleratorsPapers · 5 Nov 2026 · George Karfakis, Puneet Gupta