mlsanityData to 7 Oct 2026

LogbQuant: Quantizing Language Models in Logarithmic Space

arXiv 2607.01127 ↗First posted 1 Jul 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Quantization has become an invaluable tool to reduce memory requirements and inference speed of modern language models, in particular to make them available for consumer setups and edge devices. While previous work has primarily focused on uniform quantization codebooks, such approaches are prone to suboptimal representations due to low-frequency high-magnitude weights. We introduce LogbQuant, a novel logarithmic quantization approach with adjustable bases, to adapt to common parameter distributions. We show that our method exhibits superior performance at 4-bit precision on several performance benchmarks compared to asymmetric linear quantization at tensor-wise granularity, while achieving moderate speedup and high memory savings, making it suitable for private use on consumer-grade GPUs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 1 Jul 2026.

Builds on

29 of 44 references.

References · 29

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  4. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  5. 2016Pointer Sentinel Mixture Modelscited by 2,992
  6. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  8. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  9. 2020GLU Variants Improve Transformercited by 1,724
  10. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,338
  11. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 881
  12. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
17 more
  1. 2023A Simple and Effective Pruning Approach for Large Language Modelscited by 776
  2. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 643
  3. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
  4. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  5. 2019Understanding Straight-Through Estimator in Training Activation Quantized Neural Netscited by 225
  6. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 200
  7. 2022Language model compression with weighted low-rank factorizationcited by 192
  8. 2022FP8 Formats for Deep Learningcited by 187
  9. 2024RedPajama: an Open Dataset for Training Large Language Modelscited by 178
  10. 2021Understanding and Overcoming the Challenges of Efficient Transformer Quantizationcited by 139
  11. 2024AI and Memory Wallcited by 89
  12. 2025GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibrationcited by 54
  13. 2024VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Modelscited by 53
  14. 2024MoDeGPT: Modular Decomposition for Large Language Model Compressioncited by 45
  15. 2024SlimGPT: Layer-wise Structured Pruning for Large Language Modelscited by 43
  16. 2022Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networkscited by 26
  17. 2025ADALog: Adaptive Unsupervised Anomaly detection in Logs with Self-attention Masked Language Modelcited by 1

Built on by

Not cited yet.