# MELTing point: Mobile Evaluation of Language Transformers

arXiv: https://arxiv.org/abs/2403.12844 · HTML: https://mlsanity.com/paper/2403.12844/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 74 of its 118 references that are in the map.
- First posted on arXiv 19 Mar 2024.

## Builds on (most cited first, 30 of 74)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)

## Built on by (most cited first, 30 of 36)

- [On-Device Language Models: A Comprehensive Review](https://mlsanity.com/paper/2409.00088/) (2024)
- [Ten Challenging Problems in Federated Foundation Models](https://mlsanity.com/paper/2502.12176/) (2025)
- [Edge-First Language Model Inference: Models, Metrics, and Tradeoffs](https://mlsanity.com/paper/2505.16508/) (2025)
- [Lightweight Neural App Control](https://mlsanity.com/paper/2410.17883/) (2024)
- [Understanding Large Language Models in Your Pockets: Performance Study on COTS Mobile Devices](https://mlsanity.com/paper/2410.03613/) (2024)
- [PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms](https://mlsanity.com/paper/2410.05315/) (2024)
- [Benchmarking Ultra-Low-Power μNPUs](https://mlsanity.com/paper/2503.22567/) (2025)
- [AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices](https://mlsanity.com/paper/2605.15206/) (2026)
- [lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models](https://mlsanity.com/paper/2510.06126/) (2025)
- [Generative AI on the Edge: Architecture and Performance Evaluation](https://mlsanity.com/paper/2411.17712/) (2024)
- [OpenPhone: Mobile Agentic Foundation Models](https://mlsanity.com/paper/2510.22009/) (2025)
- [LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load](https://mlsanity.com/paper/2603.23640/) (2026)
- [MedMobile: A mobile-sized language model with clinical capabilities](https://mlsanity.com/paper/2410.09019/) (2024)
- [Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge](https://mlsanity.com/paper/2503.09114/) (2025)
- [Smaller, Smarter, Closer: The Edge of Collaborative Generative AI](https://mlsanity.com/paper/2505.16499/) (2025)
- [ConsumerBench: Benchmarking Generative AI Applications on End-User Devices](https://mlsanity.com/paper/2506.17538/) (2025)
- [P/D-Device: Disaggregated Large Language Model between Cloud and Devices](https://mlsanity.com/paper/2508.09035/) (2025)
- [Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents](https://mlsanity.com/paper/2511.07397/) (2025)
- [FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment](https://mlsanity.com/paper/2602.02680/) (2026)
- [Toward Zero-Egress Psychiatric AI: On-Device LLM Deployment for Privacy-Preserving Mental Health Decision Support](https://mlsanity.com/paper/2604.18302/) (2026)
- [Parameter-Free Encoders Remain Viable for RDB Foundation Models](https://mlsanity.com/paper/2607.05476/) (2026)
- [PELM: Power Efficient On-Device LLM Inference with Speculative Decoding and Dynamic Voltage Frequency Scaling](https://mlsanity.com/paper/2609.09662/) (2026)
- [CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloads](https://mlsanity.com/paper/2409.01089/) (2024)
- [Incentivizing Multi-Tenant Split Federated Learning for Foundation Models at the Network Edge](https://mlsanity.com/paper/2503.04971/) (2025)
- [Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study](https://mlsanity.com/paper/2606.21428/) (2026)
- [Hydra: Phase-Aware Workload Characterization of LLM Inference across Edge SoC Generations, Backends, and Quantization Levels](https://mlsanity.com/paper/2608.25053/) (2026)
- [BurTorch: Revisiting Training from First Principles by Coupling Autodiff, Math Optimization, and Systems](https://mlsanity.com/paper/2503.13795/) (2025)
- [TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices](https://mlsanity.com/paper/2506.13514/) (2025)
- [Sustainability Is Not Linear: Quantifying Performance, Energy, and Privacy Trade-offs in On-Device Intelligence](https://mlsanity.com/paper/2603.26603/) (2026)
- [LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models](https://mlsanity.com/paper/2605.17653/) (2026)

## Abstract (arXiv)

Transformers have revolutionized the machine learning landscape, gradually making their way into everyday tasks and equipping our computers with "sparks of intelligence". However, their runtime requirements have prevented them from being broadly deployed on mobile. As personal devices become increasingly powerful and prompt privacy becomes an ever more pressing issue, we explore the current state of mobile execution of Large Language Models (LLMs). To achieve this, we have created our own automation infrastructure, MELT, which supports the headless execution and benchmarking of LLMs on device, supporting different models, devices and frameworks, including Android, iOS and Nvidia Jetson devices. We evaluate popular instruction fine-tuned LLMs and leverage different frameworks to measure their end-to-end and granular performance, tracing their memory and energy requirements along the way. Our analysis is the first systematic study of on-device LLM execution, quantifying performance, energy efficiency and accuracy across various state-of-the-art models and showcases the state of on-device intelligence in the era of hyperscale models. Results highlight the performance heterogeneity across targets and corroborates that LLM inference is largely memory-bound. Quantization drastically reduces memory requirements and renders execution viable, but at a non-negligible accuracy cost. Drawing from its energy footprint and thermal behavior, the continuous execution of LLMs remains elusive, as both factors negatively affect user experience. Last, our experience shows that the ecosystem is still in its infancy, and algorithmic as well as hardware breakthroughs can significantly shift the execution cost. We expect NPU acceleration, and framework-hardware co-design to be the biggest bet towards efficient standalone execution, with the alternative of offloading tailored towards edge deployments.