{"id":"https://openalex.org/W4414539870","doi":"https://doi.org/10.1109/icc52391.2025.11161569","title":"Generative AI on the Edge: Architecture and Performance Evaluation","display_name":"Generative AI on the Edge: Architecture and Performance Evaluation","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4414539870","doi":"https://doi.org/10.1109/icc52391.2025.11161569"},"language":"en","primary_location":{"id":"doi:10.1109/icc52391.2025.11161569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019211839","display_name":"Zeinab Nezami","orcid":"https://orcid.org/0000-0002-5962-5908"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zeinab Nezami","raw_affiliation_strings":["School of Electronic and Electrical Engineering, University of Leeds,UK"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, University of Leeds,UK","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090771677","display_name":"Maryam Hafeez","orcid":"https://orcid.org/0000-0002-3735-1627"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maryam Hafeez","raw_affiliation_strings":["School of Electronic and Electrical Engineering, University of Leeds,UK"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, University of Leeds,UK","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059170546","display_name":"Karim Djemame","orcid":"https://orcid.org/0000-0001-5811-5263"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Karim Djemame","raw_affiliation_strings":["School of Computing, University of Leeds,UK"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Leeds,UK","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011903629","display_name":"Syed Ali Raza Zaidi","orcid":"https://orcid.org/0000-0003-1969-3727"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Syed Ali Raza Zaidi","raw_affiliation_strings":["School of Electronic and Electrical Engineering, University of Leeds,UK"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, University of Leeds,UK","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019211839"],"corresponding_institution_ids":["https://openalex.org/I130828816"],"apc_list":null,"apc_paid":null,"fwci":8.5176,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97621938,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4595","last_page":"4602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.829200029373169,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.829200029373169,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.7860999703407288,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.7020000219345093,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.7246000170707703},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6607000231742859},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6351000070571899},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.59579998254776},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5644000172615051},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5349000096321106},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.5012999773025513},{"id":"https://openalex.org/keywords/modularity","display_name":"Modularity (biology)","score":0.4830999970436096},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.48100000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930999994277954},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.7246000170707703},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6607000231742859},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6351000070571899},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.59579998254776},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5349000096321106},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.5012999773025513},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.48100000619888306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37369999289512634},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3528999984264374},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3492000102996826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C2985745059","wikidata":"https://www.wikidata.org/wiki/Q245","display_name":"Raspberry pi","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C2778505942","wikidata":"https://www.wikidata.org/wiki/Q18344624","display_name":"Microservices","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc52391.2025.11161569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6265269851","display_name":null,"funder_award_id":"EP/Y037421/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2136848157","https://openalex.org/W2618530766","https://openalex.org/W2624989916","https://openalex.org/W2895432151","https://openalex.org/W2903650079","https://openalex.org/W3043571714","https://openalex.org/W3129831491","https://openalex.org/W4321636575","https://openalex.org/W4387321091","https://openalex.org/W4400275494","https://openalex.org/W4405031232"],"related_works":[],"abstract_inverted_index":{"6G's":[0],"AI":[1,24],"native":[2],"vision":[3],"of":[4,22,44,70,147,165],"embedding":[5],"advance":[6],"intelligence":[7],"in":[8,55,190,195],"the":[9,16,42,185],"network":[10],"while":[11],"bringing":[12],"it":[13],"closer":[14],"to":[15,167],"user":[17],"requires":[18],"a":[19,90,113,119,162],"systematic":[20],"evaluation":[21],"Generative":[23],"(GenAI)":[25],"models":[26],"on":[27,34,75,89,112,184,201],"edge":[28,77,98,159,186],"devices.":[29],"Rapidly":[30],"emerging":[31],"solutions":[32],"based":[33],"Open":[35],"RAN":[36],"(ORAN)":[37],"and":[38,50,66,109,132,139,154,177],"Network-in-aBox":[39],"strongly":[40],"advocate":[41],"use":[43],"low-cost,":[45],"off-the-shelf":[46],"components":[47],"for":[48,53,100],"simpler":[49],"efficient":[51],"deployment,":[52],"example,":[54],"provisioning":[56],"rural":[57],"connectivity.":[58],"In":[59],"this":[60],"context,":[61],"conceptual":[62],"architecture,":[63],"hardware":[64],"testbeds,":[65],"precise":[67],"performance":[68],"quantification":[69],"Large":[71],"Language":[72],"Models":[73],"(LLMs)":[74],"off-theshelf":[76],"devices":[78],"remain":[79],"largely":[80],"unexplored.":[81],"This":[82],"research":[83],"investigates":[84],"computationally":[85],"demanding":[86],"LLM":[87],"inference":[88,189],"single":[91],"commodity":[92],"Raspberry":[93,114],"Pi":[94,115],"serving":[95],"as":[96,151],"an":[97],"testbed":[99],"ORAN.":[101],"We":[102,128,180],"investigate":[103],"various":[104],"LLMs,":[105],"including":[106],"small,":[107],"medium,":[108],"large":[110],"models,":[111,149],"5":[116,166],"Cluster":[117],"using":[118],"lightweight":[120,148],"Kubernetes":[121],"distribution":[122],"(K3s)":[123],"with":[124,172],"modular":[125],"prompting":[126],"implementation.":[127],"study":[129],"its":[130],"feasibility":[131],"limitations":[133],"by":[134],"analyzing":[135],"throughput,":[136],"latency,":[137],"accuracy,":[138],"efficiency.":[140],"Our":[141],"findings":[142],"indicate":[143],"that":[144,182],"CPU-only":[145],"deployment":[146],"such":[150],"Yi,":[152],"Phi,":[153],"Llama3,":[155],"can":[156],"effectively":[157],"support":[158],"applications,":[160],"achieving":[161],"generation":[163],"throughput":[164],"12":[168],"tokens":[169],"per":[170],"second":[171],"less":[173],"than":[174],"50%":[175],"CPU":[176],"RAM":[178],"usage.":[179],"conclude":[181],"GenAI":[183],"offers":[187],"localized":[188],"remote":[191],"or":[192],"bandwidthconstrained":[193],"environments":[194],"6":[196],"G":[197],"networks":[198],"without":[199],"reliance":[200],"cloud":[202],"infrastructure.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
