# UltraSketchLLM: Sub-1-Bit LLM Compression via Sketch and Hardware-Friendly Operators

arXiv: https://arxiv.org/abs/2506.17255 · HTML: https://mlsanity.com/paper/2506.17255/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 8 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [Extreme Compression of Large Language Models via Additive Quantization](https://mlsanity.com/paper/2401.06118/) (2024)
- [Compressing Neural Networks with the Hashing Trick](https://mlsanity.com/paper/1504.04788/) (2015)
- [What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation](https://mlsanity.com/paper/2403.06408/) (2024)
- [HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference](https://mlsanity.com/paper/2502.03589/) (2025)
- [Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing](https://mlsanity.com/paper/2207.10702/) (2022)

## Abstract (arXiv)

Large language models (LLMs) require larger GPU memory size these days, necessitating efficient and extreme weight compression methods. Existing compression methods are either theoretically limited by 1 bit per weight or face severe performance degradation and inefficiency. To deploy LLMs in resource-constrained scenarios, we introduce UltraSketchLLM, compressing LLMs with data sketch. It reduces peak GPU memory footprint with a high compression rate down to 0.5 bit per weight. Combined with hardware-friendly implementation, UltraSketchLLM keeps tolerable performance degradation and extremely low latency overhead with 14.9x speedup compared to naive sketch solution.