{"id":"https://openalex.org/W6925465844","doi":"https://doi.org/10.18420/inf2024_104","title":"LLMs on the Edge: Quality, Latency, and Energy Efficiency","display_name":"LLMs on the Edge: Quality, Latency, and Energy Efficiency","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6925465844","doi":"https://doi.org/10.18420/inf2024_104"},"language":"en","primary_location":{"id":"doi:10.18420/inf2024_104","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_104","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/inf2024_104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bast, Sebastian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bast, Sebastian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Begic Fazlic, Lejla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Begic Fazlic, Lejla","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Naumann, Stefan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naumann, Stefan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Dartmann, Guido","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dartmann, Guido","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9669,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92715642,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12573","display_name":"Education and Digital Technologies","score":0.043800000101327896,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12573","display_name":"Education and Digital Technologies","score":0.043800000101327896,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12343","display_name":"Geography Education and Pedagogy","score":0.031199999153614044,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13084","display_name":"Education during COVID-19 pandemic","score":0.028999999165534973,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.6912999749183655},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5454999804496765},{"id":"https://openalex.org/keywords/sustainability","display_name":"Sustainability","score":0.4993000030517578},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4941999912261963},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.484499990940094},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.47620001435279846},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4745999872684479}],"concepts":[{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6912999749183655},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5163999795913696},{"id":"https://openalex.org/C66204764","wikidata":"https://www.wikidata.org/wiki/Q219416","display_name":"Sustainability","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.484499990940094},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C134560507","wikidata":"https://www.wikidata.org/wiki/Q753291","display_name":"Environmental economics","level":1,"score":0.460999995470047},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45320001244544983},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2700999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C552854447","wikidata":"https://www.wikidata.org/wiki/Q131201","display_name":"Sustainable development","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18420/inf2024_104","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_104","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18420/inf2024_104","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_104","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"score":0.8141953945159912,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"Artificial":[1],"Intelligence":[2],"has":[3],"become":[4],"integral":[5],"to":[6,28,36,45,66,101,105],"many":[7],"people's":[8],"lives,":[9],"with":[10,59],"Large":[11],"Language":[12],"Models":[13],"(LLMs)":[14],"gaining":[15],"popularity":[16],"in":[17,149],"both":[18],"science":[19],"and":[20,79,110,114],"society.":[21],"While":[22],"training":[23],"these":[24],"models":[25,88,133],"is":[26],"known":[27],"require":[29],"significant":[30],"energy,":[31],"inference":[32],"also":[33],"contributes":[34],"substantially":[35],"their":[37],"total":[38],"energy":[39,80,118],"consumption.":[40,81],"This":[41],"study":[42],"investigates":[43],"how":[44],"use":[46],"LLMs":[47,71],"sustainably":[48],"by":[49],"examining":[50],"the":[51,68],"efficiency":[52,69,143],"of":[53,70,84,117],"inference,":[54],"particularly":[55],"on":[56,72,76,89,121,138],"local":[57],"hardware":[58],"limited":[60],"computing":[61],"resources.":[62],"We":[63],"develop":[64],"metrics":[65],"quantify":[67],"edge":[73,90,139],"devices,":[74,140],"focusing":[75],"quality,":[77],"latency,":[78],"Our":[82],"comparison":[83],"three":[85],"state-of-the-art":[86],"generative":[87,132],"devices":[91],"shows":[92],"that":[93,131],"they":[94],"achieve":[95],"quality":[96],"scores":[97],"ranging":[98],"from":[99],"73.3%":[100],"85.9%,":[102],"generate":[103],"1.83":[104],"3.51":[106],"tokens":[107],"per":[108,119],"second,":[109],"consume":[111],"between":[112],"0.93":[113],"1.76":[115],"mWh":[116],"token":[120],"a":[122],"single-board":[123],"computer":[124],"without":[125],"GPU":[126],"support.":[127],"The":[128],"findings":[129],"suggest":[130],"can":[134],"produce":[135],"satisfactory":[136],"outcomes":[137],"but":[141],"thorough":[142],"evaluations":[144],"are":[145],"recommended":[146],"before":[147],"deployment":[148],"production":[150],"environments.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
