{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:30:58Z","timestamp":1771612258297,"version":"3.50.1"},"reference-count":11,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-009"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-001"}],"funder":[{"DOI":"10.13039\/501100011033","name":"Agencia Estatal de Investigaci\u00f3n","doi-asserted-by":"publisher","award":["FUN4DATE (PID2022-136684OB-C22)"],"award-info":[{"award-number":["FUN4DATE (PID2022-136684OB-C22)"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SMARTY","award":["101140087"],"award-info":[{"award-number":["101140087"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computer"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/mc.2024.3399384","type":"journal-article","created":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T17:21:23Z","timestamp":1723224083000},"page":"74-80","source":"Crossref","is-referenced-by-count":4,"title":["Speed and Conversational Large Language Models: Not All Is About Tokens per Second"],"prefix":"10.1109","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5304-0626","authenticated-orcid":false,"given":"Javier","family":"Conde","sequence":"first","affiliation":[{"name":"ETSI de Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain"}]},{"given":"Miguel","family":"Gonz\u00e1lez","sequence":"additional","affiliation":[{"name":"ETSI de Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2540-5234","authenticated-orcid":false,"given":"Pedro","family":"Reviriego","sequence":"additional","affiliation":[{"name":"ETSI de Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9887-1418","authenticated-orcid":false,"given":"Zhen","family":"Gao","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6226-2880","authenticated-orcid":false,"given":"Shanshan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3152-3245","authenticated-orcid":false,"given":"Fabrizio","family":"Lombardi","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/jas.2023.123618"},{"key":"ref2","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref3","article-title":"Gemini: A family of highly capable multimodal models","year":"2023"},{"key":"ref4","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-55560-2_5"},{"key":"ref6","first-page":"1","article-title":"Measuring massive multitask language understanding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2021"},{"key":"ref7","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","author":"Zheng","year":"2023"},{"key":"ref8","volume-title":"LLM-Perf Leaderboard","author":"Moutawwakil","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ieeestd.2020.9091348"},{"key":"ref10","article-title":"AWQ: Activation-aware weight quantization for LLM compression and acceleration","author":"Lin","year":"2023"},{"key":"ref11","article-title":"The era of 1-bit LLMs: All large language models are in 1.58 bits","author":"Ma","year":"2024"}],"container-title":["Computer"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2\/10632595\/10632720.pdf?arnumber=10632720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T17:27:31Z","timestamp":1724088451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10632720\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":11,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/mc.2024.3399384","relation":{},"ISSN":["0018-9162","1558-0814"],"issn-type":[{"value":"0018-9162","type":"print"},{"value":"1558-0814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}