{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:27:33Z","timestamp":1783542453131,"version":"3.55.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472452"],"award-info":[{"award-number":["62472452"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2025A1515010262"],"award-info":[{"award-number":["2025A1515010262"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tmc.2026.3674827","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:41:12Z","timestamp":1773862872000},"page":"13077-13094","source":"Crossref","is-referenced-by-count":1,"title":["Understanding Large Language Models in Your Pockets: Performance Study on COTS Mobile Devices"],"prefix":"10.1109","volume":"25","author":[{"given":"Jie","family":"Xiao","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9525-7754","authenticated-orcid":false,"given":"Qianyi","family":"Huang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9943-6020","authenticated-orcid":false,"given":"Xu","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2710-7628","authenticated-orcid":false,"given":"Chen","family":"Tian","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Apple intelligence","author":"Inc","year":"2024"},{"key":"ref2","article-title":"Introducing copilot PCs","author":"Mehdi","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3773080"},{"key":"ref4","article-title":"Chatgpt","author":"AI","year":"2022"},{"key":"ref5","article-title":"Claude","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3706418"},{"key":"ref7","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref8","article-title":"Mistral 7b","author":"Jiang","year":"2023"},{"key":"ref9","first-page":"1","article-title":"LLM as a system service on mobile devices","volume-title":"Proc. 24th ACM\/IEEE Int. Conf. Embedded Artif. Intell. Sens. Syst.","author":"Yin","year":"2026"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3690668"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3662006.3662059"},{"key":"ref12","article-title":"MobileAIBench: Benchmarking LLMs and LMMs for on-device use cases","author":"Murthy","year":"2024"},{"key":"ref13","article-title":"Llama 3.2 - model cards & prompt formats","year":"2025"},{"key":"ref14","article-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"ref15","article-title":"Gemma 3 technical report","author":"Team","year":"2025"},{"key":"ref16","article-title":"llama.cpp: LLM inference in c\/c","author":"Gerganov","year":"2023"},{"key":"ref17","article-title":"MLC-LLM","year":"2023"},{"key":"ref18","article-title":"Snapdragon profiler","year":"2023"},{"key":"ref19","article-title":"Arm streamline","year":"2024"},{"key":"ref20","article-title":"Xcode","year":"2025"},{"key":"ref21","article-title":"Big.little technology: The future of mobile","year":"2013"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"3214","DOI":"10.18653\/v1\/2022.acl-long.229","article-title":"TruthfulQA: Measuring how models mimic human falsehoods","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics (Volume 1: Long Papers)","author":"Lin","year":"2022"},{"key":"ref23","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3451185"},{"key":"ref25","article-title":"Towards ai search paradigm","author":"Li","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0950"},{"key":"ref27","first-page":"29082","article-title":"Sheared LLaMA: Accelerating language model pre-training via structured pruning","volume-title":"Proc. 12th Int. Conf. Learn.","author":"Xia","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.conll-babylm.24"},{"key":"ref29","article-title":"Tensorgpt: Efficient compression of the embedding layer in llms based on the tensor-train decomposition","author":"Xu","year":"2023"},{"key":"ref30","first-page":"1","article-title":"Dynamic sparse attention on mobile socs","volume-title":"Proc. 24th ACM Int. Conf. Mobile Syst., Appl., Serv.","author":"Yin","year":"2026"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref32","first-page":"1","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Frantar","year":"2023"},{"key":"ref33","first-page":"87","article-title":"AWQ: Activationaware weight quantization for LLM compression and acceleration","volume-title":"Proc. Mach. Learn. Syst","volume":"6","author":"Lin","year":"2024"},{"key":"ref34","article-title":"k-quants","author":"Gerganov","year":"2024"},{"key":"ref35","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao","year":"2023"},{"key":"ref36","article-title":"A speed odyssey for deployable quantization of LLMs","author":"Li","year":"2023"},{"key":"ref37","article-title":"Fast transformer decoding: One write-head is all you need","author":"Shazeer","year":"2019"},{"key":"ref38","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref39","article-title":"Phi open models","year":"2024"},{"key":"ref40","article-title":"Gemini","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/jsac.2025.3645168"},{"key":"ref42","article-title":"MNN-LLM","year":"2023"},{"key":"ref43","article-title":"mllm: Fast and lightweight multimodal LLM inference engine for mobile and edge devices","author":"Yi","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00447"},{"key":"ref45","article-title":"Unlocking on-device generative AI with an NPU and heterogeneous computing","year":"2024","journal-title":""},{"key":"ref46","article-title":"Mediatek-dimensity-9300-plus","year":"2024"},{"key":"ref47","article-title":"Perfetto: System profiling, app tracing and trace analysis","year":"2024"},{"key":"ref48","article-title":"Android debug bridge (ADB)","year":"2024"},{"key":"ref49","first-page":"1","article-title":"Measuring massive multitask language understanding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2021"},{"key":"ref50","article-title":"Think you have solved question answering? Try arc, the AI2 reasoning challenge","author":"Clark","year":"2018"},{"key":"ref51","article-title":"Dimensity 9300 all big cores whitepaper","year":"2024"},{"key":"ref52","article-title":"Smmla signed most significant word multiply with accumulation","year":"2024"},{"key":"ref53","article-title":"Optimizing large language model (LLM) inference for arm cpus","author":"Gope","year":"2024"},{"key":"ref54","article-title":"clpeak. A tool which profiles opencl devices to find their peak capacities","year":"2024"},{"key":"ref55","article-title":"Arm immortalis-g720 and arm Mali-g720 performance counters reference guide","year":"2025"},{"key":"ref56","article-title":"Harnessing qualcomm adreno gpu for generative AI: Open-source approach","year":"2025"},{"key":"ref57","article-title":"Determining the local work-group size","year":"2025"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512148"},{"key":"ref59","article-title":"Apple unleashes M1","year":"2020"},{"key":"ref60","article-title":"SVE2 architecture fundamentals","year":"2024"},{"key":"ref61","article-title":"SME and SME2. The scalable matrix extension (SME)","year":"2024"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11595771\/11440122.pdf?arnumber=11440122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:45:14Z","timestamp":1783539914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11440122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":61,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2026.3674827","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}