# GPTQT: Quantize Large Language Models Twice to Push the Efficiency

arXiv: https://arxiv.org/abs/2407.02891 · HTML: https://mlsanity.com/paper/2407.02891/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 13 of 13)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2309.14717/) (2023)
- [BiLLM: Pushing the Limit of Post-Training Quantization for LLMs](https://mlsanity.com/paper/2402.04291/) (2024)
- [LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models](https://mlsanity.com/paper/2206.09557/) (2022)
- [Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modelling](https://mlsanity.com/paper/1904.04733/) (2019)

## Built on by (most cited first, 4 of 4)

- [VEXP: A Low-Cost RISC-V ISA Extension for Accelerated Softmax Computation in Transformers](https://mlsanity.com/paper/2504.11227/) (2025)
- [STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization](https://mlsanity.com/paper/2510.26771/) (2025)
- [Calibration and Transformation-Free Weight-Only LLMs Quantization via Dynamic Grouping](https://mlsanity.com/paper/2509.03054/) (2025)
- [QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization](https://mlsanity.com/paper/2609.00224/) (2026)

## Abstract (arXiv)

Due to their large size, generative Large Language Models (LLMs) require significant computing and storage resources. This paper introduces a new post-training quantization method, GPTQT, to reduce memory usage and enhance processing speed by expressing the weight of LLM in 3bit/2bit. Practice has shown that minimizing the quantization error of weights is ineffective, leading to overfitting. Therefore, GPTQT employs a progressive two-step approach: initially quantizing weights using Linear quantization to a relatively high bit, followed by converting obtained int weight to lower bit binary coding. A re-explore strategy is proposed to optimize initial scaling factor. During inference, these steps are merged into pure binary coding, enabling efficient computation. Testing across various models and datasets confirms GPTQT's effectiveness. Compared to the strong 3-bit quantization baseline, GPTQT further reduces perplexity by 4.01 on opt-66B and increases speed by 1.24 times on opt-30b. The results on Llama2 show that GPTQT is currently the best binary coding quantization method for such kind of LLMs.