# SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization

arXiv: https://arxiv.org/abs/2412.04180 · HTML: https://mlsanity.com/paper/2412.04180/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 5 Dec 2024.

## Builds on (most cited first, 30 of 33)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models](https://mlsanity.com/paper/2308.13137/) (2023)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [LLM-QAT: Data-Free Quantization Aware Training for Large Language Models](https://mlsanity.com/paper/2305.17888/) (2023)
- [SqueezeLLM: Dense-and-Sparse Quantization](https://mlsanity.com/paper/2306.07629/) (2023)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [ZeroQ: A Novel Zero Shot Quantization Framework](https://mlsanity.com/paper/2001.00281/) (2020)
- [Coordinate Descent Algorithms](https://mlsanity.com/paper/1502.04759/) (2015)
- [GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference](https://mlsanity.com/paper/2005.03842/) (2020)
- [AI and Memory Wall](https://mlsanity.com/paper/2403.14123/) (2024)
- [Full Stack Optimization of Transformer Inference: a Survey](https://mlsanity.com/paper/2302.14017/) (2023)
- [Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation](https://mlsanity.com/paper/2111.14826/) (2021)
- [ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training](https://mlsanity.com/paper/2104.14129/) (2021)
- [GACT: Activation Compressed Training for Generic Network Architectures](https://mlsanity.com/paper/2206.11357/) (2022)
- [Deep Neural Network Compression with Single and Multiple Level Quantization](https://mlsanity.com/paper/1803.03289/) (2018)
- [ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models](https://mlsanity.com/paper/2408.08554/) (2024)

## Built on by (most cited first, 6 of 6)

- [GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance](https://mlsanity.com/paper/2505.07004/) (2025)
- [StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths](https://mlsanity.com/paper/2601.19320/) (2026)
- [LCD: Advancing Extreme Low-Bit Clustering for Large Language Models via Knowledge Distillation](https://mlsanity.com/paper/2506.12038/) (2025)
- [Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization](https://mlsanity.com/paper/2607.00908/) (2026)
- [SAB-LVLM: Significance-Aware Binarization for Large Vision-Language Models](https://mlsanity.com/paper/2607.01876/) (2026)
- [QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching](https://mlsanity.com/paper/2602.12609/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) exhibit impressive performance across various tasks, but deploying them for inference poses challenges. Their high resource demands often necessitate complex, costly multi-GPU pipelines, or the use of smaller, less capable models. While quantization offers a promising solution utilizing lower precision for model storage, existing methods frequently experience significant performance drops at lower precision levels. Additionally, they typically provide only a limited set of solutions at specific bit levels, many of which are extensively manually tuned. To address these challenges, we propose a new method called SKIM: Scaled K-means clustering wIth Mixed precision. Our approach introduces two novel techniques: 1. A greedy algorithm to solve approximately optimal bit allocation across weight channels, and 2. A trainable scaling vector for non-differentiable K-means clustering. These techniques substantially improve performance and can be adapted to any given bit. Notably, in terms of model perplexity, our method narrows the gap between 3-bit quantized LLaMA models and their full precision counterparts by 16.3% on average.