# Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deployment

arXiv: https://arxiv.org/abs/2608.15693 · HTML: https://mlsanity.com/paper/2608.15693/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 66 references that are in the map.
- First posted on arXiv 16 Aug 2026.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding](https://mlsanity.com/paper/2012.02951/) (2020)
- [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024)
- [A Review on Edge Large Language Models: Design, Execution, and Applications](https://mlsanity.com/paper/2410.11845/) (2024)
- [Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models](https://mlsanity.com/paper/2503.06027/) (2025)
- [Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators](https://mlsanity.com/paper/2302.08469/) (2023)
- [HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks](https://mlsanity.com/paper/2301.09422/) (2023)
- [MobileQuant: Mobile-friendly Quantization for On-device Language Models](https://mlsanity.com/paper/2408.13933/) (2024)
- [GenAI at the Edge: Comprehensive Survey on Empowering Edge Devices](https://mlsanity.com/paper/2502.15816/) (2025)
- [Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey](https://mlsanity.com/paper/2505.01821/) (2025)
- [Quantization of Deep Neural Networks for Accurate Edge Computing](https://mlsanity.com/paper/2104.12046/) (2021)
- [Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration](https://mlsanity.com/paper/2507.00672/) (2025)
- [Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment](https://mlsanity.com/paper/2501.03265/) (2025)
- [Leveraging LLM Tutoring Systems for Non-Native English Speakers in Introductory CS Courses](https://mlsanity.com/paper/2411.02725/) (2024)
- [EdgeShard: Efficient LLM Inference via Collaborative Edge Computing](https://mlsanity.com/paper/2405.14371/) (2024)
- [Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices](https://mlsanity.com/paper/2102.07071/) (2021)
- [Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities](https://mlsanity.com/paper/2604.22906/) (2026)

## Abstract (arXiv)

Running large AI models on resource-constrained edge devices requires model compression to reduce model size and computation. What compresses well, however, need not deploy well. We survey dozens of recent works that report compression results on real hardware and extract practical deployment guidelines from them. Following these guidelines, we deploy compact language and image models on GPU, CPU, and Raspberry Pi platforms across question answering and image segmentation. No single technique wins across tasks. For question answering, Qwen3.5 0.8B reaches 93.85 SQuAD F1 and 92 EM under Q5_K_M GGUF quantization, while structured pruning at the same precision costs 16 F1 at a 1% ratio. For segmentation, the ranking reverses: default quantization leaves parameters and MACs unchanged, whereas pruning cuts model size by nearly 80% at near-constant mIoU. Pruning can even inflate the deployed artifact by 21-49% by breaking k-quant super-block alignment; combined with longer, less format-compliant outputs, this raises Raspberry Pi latency up to 3.4x. Compression can also manufacture the appearance of competence rather than destroy it visibly: one LoRA-recovered variant stays fully parseable and holds 71% strict BoolQ accuracy while sending 97 of 100 predictions to a single class, at 52.6% balanced accuracy. We explain these effects through neural-flow graph analysis and prefill-decode-level latency decomposition, and condense them into task-specific deployment research directions. The right technique depends on the task, the model, and the hardware. Our experiment code and artifacts are open-sourced at https://github.com/Arnavvvkumar/deployment