# ZipLLM: Efficient LLM Storage via Model-Aware Synergistic Data Deduplication and Compression

arXiv: https://arxiv.org/abs/2505.06252 · HTML: https://mlsanity.com/paper/2505.06252/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2025.

## Built on by (most cited first, 5 of 5)

- [SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving](https://mlsanity.com/paper/2605.01708/) (2026)
- [Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference](https://mlsanity.com/paper/2605.09990/) (2026)
- [Lossless Tensor Compression as Program Synthesis](https://mlsanity.com/paper/2608.02162/) (2026)
- [TensorDex: A Compact, Tensor-Centric Storage System for Modern AI Models](https://mlsanity.com/paper/2604.17104/) (2026)
- [Block-Level Weight-Space Structure Persists Under Post-Training: An Empirical Study Across LLM Families](https://mlsanity.com/paper/2609.26147/) (2026)

## Abstract (arXiv)

Modern model hubs, such as Hugging Face, store tens of petabytes of LLMs, with fine-tuned variants vastly outnumbering base models and dominating storage consumption. Existing storage reduction techniques -- such as deduplication and compression -- are either LLM-oblivious or not compatible with each other, limiting data reduction effectiveness. Our large-scale characterization study across all publicly available Hugging Face LLM repositories reveals several key insights: (1) fine-tuned models within the same family exhibit highly structured, sparse parameter differences suitable for delta compression; (2) bitwise similarity enables LLM family clustering; and (3) tensor-level deduplication is better aligned with model storage workloads, achieving high data reduction with low metadata overhead. Building on these insights, we design BitX, an effective, fast, lossless delta compression algorithm that compresses XORed difference between fine-tuned and base LLMs. We build ZipLLM, a model storage reduction pipeline that unifies tensor-level deduplication and lossless BitX compression. By synergizing deduplication and compression around LLM family clustering, ZipLLM reduces model storage consumption by 54%, over 20% higher than state-of-the-art deduplication and compression approaches.