# From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices

arXiv: https://arxiv.org/abs/2507.23536 · HTML: https://mlsanity.com/paper/2507.23536/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection](https://mlsanity.com/paper/2403.03507/) (2024)
- [Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing](https://mlsanity.com/paper/1905.10083/) (2019)
- [Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs](https://mlsanity.com/paper/2003.00152/) (2020)
- [SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models](https://mlsanity.com/paper/2308.06522/) (2023)
- [Test-Time Model Adaptation with Only Forward Passes](https://mlsanity.com/paper/2404.01650/) (2024)
- [μNAS: Constrained Neural Architecture Search for Microcontrollers](https://mlsanity.com/paper/2010.14246/) (2020)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading](https://mlsanity.com/paper/2206.07509/) (2022)
- [The Entropy Enigma: Success and Failure of Entropy Minimization](https://mlsanity.com/paper/2405.05012/) (2024)
- [REDS: Resource-Efficient Deep Subnetworks for Dynamic Resource Constraints](https://mlsanity.com/paper/2311.13349/) (2023)

## Built on by (most cited first, 4 of 4)

- [On-Device Fine-Tuning via Backprop-Free Zeroth-Order Optimization](https://mlsanity.com/paper/2511.11362/) (2025)
- [DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems](https://mlsanity.com/paper/2604.05375/) (2026)
- [Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices](https://mlsanity.com/paper/2606.19528/) (2026)
- [On the Interaction Between Model Compression and Test-Time Adaptation](https://mlsanity.com/paper/2609.03604/) (2026)

## Abstract (arXiv)

Parameter-efficient fine-tuning (PEFT) methods reduce the computational costs of updating deep learning models by minimizing the number of additional parameters used to adapt a model to a down- stream task. While extensively researched in large language models (LLMs), their application to smaller models used on edge devices, such as convolutional neural networks, remains underexplored. This paper benchmarks and analyzes popular PEFT methods on convolutional architectures typically deployed in resource-constrained edge environments. We evaluate LoRA, DoRA, and GaLore for updating standard and depthwise convolutional architectures to handle distribution shifts and accommodate unseen classes. We utilize recently proposed PyTorch profilers to compare the updated model performance and computational costs of these PEFT methods with traditional fine-tuning approaches. With resource efficiency in mind, we investigate their update behavior across different rank dimensions. We find that the evaluated PEFT methods are only half as memory-efficient when applied to depthwise-separable convolution architectures, compared to their efficiency with LLMs. Conversely, when targeting convolu- tional architectures optimized for edge deployment, adapter-based PEFT methods can reduce floating point operations (FLOPs) during model updates by up to 95%. These insights offer valuable guidance for selecting PEFT methods based on hardware constraints, performance requirements, and application needs. Our code is online.