{"id":"https://openalex.org/W4416250140","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228317","title":"LLMs at the Edge: Performance and Efficiency Evaluation with Ollama on Diverse Hardware","display_name":"LLMs at the Edge: Performance and Efficiency Evaluation with Ollama on Diverse Hardware","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250140","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228317"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5068938035","display_name":"Donghao Huang","orcid":"https://orcid.org/0009-0005-6767-4872"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Donghao Huang","raw_affiliation_strings":["Singapore Management University,School of Computing and Information Systems,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information Systems,Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003218042","display_name":"Zhaoxia Wang","orcid":"https://orcid.org/0000-0001-7674-5488"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhaoxia Wang","raw_affiliation_strings":["Singapore Management University,School of Computing and Information Systems,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,School of Computing and Information Systems,Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0704,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80943282,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12238","display_name":"Green IT and Sustainability","score":0.5310999751091003,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12238","display_name":"Green IT and Sustainability","score":0.5310999751091003,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.1281999945640564,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T14347","display_name":"Big Data and Digital Economy","score":0.0357000008225441,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/software-deployment","display_name":"Software deployment","score":0.7577000260353088},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.7009000182151794},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.6283000111579895},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5871000289916992},{"id":"https://openalex.org/keywords/energy-conservation","display_name":"Energy conservation","score":0.41100001335144043},{"id":"https://openalex.org/keywords/consumption","display_name":"Consumption (sociology)","score":0.3765999972820282},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.36090001463890076}],"concepts":[{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7577000260353088},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.7009000182151794},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.6283000111579895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6036999821662903},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5871000289916992},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.42559999227523804},{"id":"https://openalex.org/C520301825","wikidata":"https://www.wikidata.org/wiki/Q380170","display_name":"Energy conservation","level":2,"score":0.41100001335144043},{"id":"https://openalex.org/C30772137","wikidata":"https://www.wikidata.org/wiki/Q5164762","display_name":"Consumption (sociology)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3240000009536743},{"id":"https://openalex.org/C552854447","wikidata":"https://www.wikidata.org/wiki/Q131201","display_name":"Sustainable development","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3093000054359436},{"id":"https://openalex.org/C2989164559","wikidata":"https://www.wikidata.org/wiki/Q15637420","display_name":"Low energy","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2780331096","wikidata":"https://www.wikidata.org/wiki/Q24965464","display_name":"Energy modeling","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C17058734","wikidata":"https://www.wikidata.org/wiki/Q1064441","display_name":"Democratization","level":4,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2979826702","https://openalex.org/W4372260185","https://openalex.org/W4395704222","https://openalex.org/W4406164090","https://openalex.org/W4408566262","https://openalex.org/W4409116517"],"related_works":[],"abstract_inverted_index":{"Energy":[0],"efficiency":[1,50],"is":[2],"a":[3],"critical":[4],"consideration":[5],"in":[6],"deploying":[7],"large":[8],"language":[9],"models":[10,146,158],"(LLMs)":[11],"due":[12],"to":[13,93,125],"their":[14],"significant":[15],"environmental":[16],"footprint.":[17],"This":[18],"study":[19],"addresses":[20],"this":[21],"challenge":[22],"by":[23],"leveraging":[24],"Ollama,":[25],"an":[26,149],"open-source":[27,52],"framework":[28],"that":[29],"facilitates":[30],"efficient":[31,104],"local":[32],"deployment":[33,106],"of":[34,51,152,188],"LLMs,":[35],"thereby":[36,137],"reducing":[37,192],"energy":[38,135,172,193],"consumption":[39,194],"alongside":[40],"enhancing":[41],"privacy":[42],"and":[43,49,57,83,154,163,181,195],"accessibility.":[44],"We":[45],"evaluate":[46],"the":[47,55,129,160,186],"performance":[48,153,162],"LLMs":[53],"from":[54],"Qwen2.5":[56],"Llama3":[58],"families":[59],"(0.5B\u201390B":[60],"parameters)":[61],"across":[62,120],"diverse":[63],"hardware":[64,109],"platforms,":[65],"including":[66],"consumer-grade":[67],"devices.":[68],"Our":[69],"evaluation":[70],"spans":[71],"high-end":[72],"systems":[73],"(RTX":[74],"A6000,":[75],"RTX":[76],"4090),":[77],"consumer":[78,108],"laptops":[79],"like":[80,86],"Apple":[81],"M3/M4,":[82],"accessible":[84],"platforms":[85],"NVIDIA":[87],"Jetson":[88],"AGX":[89],"Orin,":[90],"showcasing":[91],"pathways":[92],"widespread":[94],"AI":[95,183],"adoption.":[96],"Key":[97],"findings":[98],"include:":[99],"(1)":[100],"Ollama\u2019s":[101],"quantization":[102],"enables":[103],"LLM":[105,189],"on":[107,140],"while":[110,132,191],"preserving":[111],"performance;":[112],"(2)":[113],"Windows":[114],"Subsystem":[115],"for":[116,128,178],"Linux":[117],"enhances":[118],"speeds":[119],"all":[121],"models,":[122],"delivering":[123],"up":[124],"21\u00d7":[126],"improvements":[127],"smallest":[130],"model":[131],"also":[133],"improving":[134],"efficiency,":[136],"broadening":[138],"adoption":[139],"common":[141],"computing":[142],"platforms;":[143],"(3)":[144],"Medium-sized":[145],"(7B\u201332B)":[147],"achieve":[148,159],"ideal":[150],"balance":[151],"efficiency;":[155],"(4)":[156],"Larger":[157],"highest":[161],"exhibit":[164],"better":[165],"cross-platform":[166],"consistency":[167],"but":[168],"are":[169],"significantly":[170],"less":[171],"efficient.":[173],"These":[174],"results":[175],"highlight":[176],"strategies":[177],"inclusive,":[179],"privacy-preserving,":[180],"sustainable":[182],"deployment,":[184],"advancing":[185],"democratization":[187],"technology":[190],"infrastructure":[196],"demands.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}
