MatGPTQ: Efficient and Accurate Inference over Nested Quantized Models

arXiv:2602.03537 · cs.LG · Submitted 2026-02-03 · Read on arXiv

cs.LG

Submitted: 2026-02-03

Updated: 2026-09-30

Code: https://github.com/IST-DASLab/MatGPTQ

Project page: https://mobiusml.github.io/hqq_blog

Terminology

• Quantization — 8× in this paper · explained in 12 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Quantization-Aware Training — 1× in this paper · explained in 3 episodes

Sources

• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• The Llama 3 Herd of Models
• TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision
• Qwen3 Technical Report
• Instruction-Following Evaluation for Large Language Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks