# D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation

arXiv: https://arxiv.org/abs/2604.16940 · HTML: https://mlsanity.com/paper/2604.16940/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data](https://mlsanity.com/paper/2410.01560/) (2024)
- [LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation](https://mlsanity.com/paper/2306.11222/) (2023)
- [LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning](https://mlsanity.com/paper/2311.12023/) (2023)
- [Parameter Competition Balancing for Model Merging](https://mlsanity.com/paper/2410.02396/) (2024)
- [Compressing Large Language Models using Low Rank and Low Precision Decomposition](https://mlsanity.com/paper/2405.18886/) (2024)
- [Multimodal Reasoning with Multimodal Knowledge Graph](https://mlsanity.com/paper/2406.02030/) (2024)
- [LQER: Low-Rank Quantization Error Reconstruction for LLMs](https://mlsanity.com/paper/2402.02446/) (2024)
- [BitDelta: Your Fine-Tune May Only Be Worth One Bit](https://mlsanity.com/paper/2402.10193/) (2024)
- [DeltaZip: Efficient Serving of Multiple Full-Model-Tuned LLMs](https://mlsanity.com/paper/2312.05215/) (2023)
- [Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals](https://mlsanity.com/paper/2305.18425/) (2023)
- [LLM Chain Ensembles for Scalable and Accurate Data Annotation](https://mlsanity.com/paper/2410.13006/) (2024)
- [Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer](https://mlsanity.com/paper/2505.18713/) (2025)
- [Knowledge Fusion of Large Language Models Via Modular SkillPacks](https://mlsanity.com/paper/2505.18502/) (2025)
- [ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs](https://mlsanity.com/paper/2504.13237/) (2025)
- [Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling](https://mlsanity.com/paper/2505.17110/) (2025)

## Built on by (most cited first, 1 of 1)

- [Dynamic Model Merging Made Slim](https://mlsanity.com/paper/2605.18904/) (2026)

## Abstract (arXiv)

Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incurs substantial memory overhead. Delta compression addresses this by retaining a single pre-trained LLM with multiple compressed delta weights. However, existing methods fail on models fine-tuned with largescale datasets. We find that larger SFT data scale amplifies delta parameter magnitude, singular values, and entropy, exacerbating compression errors. To tackle this, we propose DQRELO (Delta Compression via Quantization and Residual Low-Rank), a novel training- and data-free delta compression method. It combines coarse-grained one-bit quantization to capture the dominant structure of the delta, followed by compensated residual low-rank approximation to recover fine-grained details from the smaller residual error. Experiments on various LLMs spanning dense and MoE architectures across multiple domains under this challenging setting demonstrate that DQRELO outperforms existing methods. Moreover, we establish key design principles for delta compression through extensive empirical analysis, demonstrating how task difficulty, architecture, and layer positioning create predictable patterns that can guide optimal compression strategies in production systems.