mlsanityData to 14 Oct 2026

PolarQuant: Optimal Gaussian Weight Quantization via Hadamard Rotation for LLM Compression

arXiv 2603.29078 ↗First posted 30 Mar 2026cs.CL cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

We present PolarQuant, a post-training weight quantization method for large language models (LLMs) that exploits the distributional structure of neural network weights to achieve near-lossless compression. PolarQuant operates in three stages: (1) block-wise normalization to the unit hypersphere, (2) Walsh-Hadamard rotation to transform coordinates into approximately Gaussian random variables, and (3) quantization with centroids matched to the Gaussian distribution. Our ablation reveals that Hadamard rotation alone accounts for 98% of the quality improvement, reducing Qwen3.5-9B perplexity from 6.90 (absmax Q5) to 6.40 (Delta = +0.03 from FP16), making it practically lossless without any calibration data. Furthermore, PolarQuant functions as an effective preprocessing step for downstream INT4 quantizers: PolarQuant Q5 dequantized and re-quantized by torchao INT4 achieves perplexity 6.56 versus 6.68 for direct absmax INT4, while maintaining 43.1 tok/s throughput at 6.5 GB VRAM. Code and models are publicly available.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 8 of its 18 references that are in the map. First posted on arXiv 30 Mar 2026.

Builds on

8 of 18 references.

References · 8

  1. 2016Pointer Sentinel Mixture Modelscited by 3,096
  2. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  3. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  4. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  5. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 634
  6. 2024SpinQuant: LLM quantization with learned rotationscited by 471
  7. 2023QuIP: 2-Bit Quantization of Large Language Models With Guaranteescited by 414
  8. 2025TurboQuant: Online Vector Quantization with Near-optimal Distortion Ratecited by 125

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scalingcited by 1
  2. 2026Fast-TurboQuant: A Multiplier-Free Online Vector Quantization Approachcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CDQuant: Greedy Coordinate Descent for Accurate LLM Quantization
  2. 2025PolarQuant: Quantizing KV Caches with Polar Transformation
  3. 2026TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
  4. 2026NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models
  5. 2023FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs
  6. 2026ThinQuant: Scalable Rotation Learning for Weight and Activation Quantization of LLMs
  7. 2024CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression
  8. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models