Research map / Architectures and efficiency / Quantization
The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm
Jiale Chen, Yalda Shabanzadeh, Elvir Crnčević, Torsten Hoefler, Dan Alistarh
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use HPTQ (Huffman-encoded no-clipping GPTQ) instead of RTN, GPTQ, HRTN and SSQR | Qwen3-8B quantization · WikiText-2 | perplexity | Improved |
| use min-pivot order instead of act-order (ablation) | GPTQ quantization order · preliminary runs | downstream accuracy | No clear effect |
| enforce no-clipping by simply increasing scales (ablation) | GPTQ · layer-wise quantization error | quantization error | Hurt |
| vary HPTQ average bitwidth among 4.125, 3.125 and 2.125 (ablation) | HPTQ on Qwen3 0.6B to 14B · WikiText-2 | perplexity vs model size | Mixed |
Closest papers by meaning
- GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling (NeurIPS 2026 · similarity 0.91)
- ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models (AAAI 2025 · similarity 0.90)
- GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models (ICML 2025 · similarity 0.89)
- SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression (ICLR 2024 · similarity 0.89)
- LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid (ICLR 2025 · similarity 0.89)
- RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models (NeurIPS 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
