Research paper

MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment

Published by Association for Computational LinguisticsJul 2026PDF

Compare the design choices behind an on-device language model built around deployment latency.

MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment cover

Resource access

Get the full resource

Enter your business details to read the full resource.

First nameLast nameWork emailCompanyJob titleCountry or region

Hanxian Huang, Igor Fedorov, Andrey Gromov, Bernard Beckerman, Naveen Suda, David Eriksson, Maximilian Balandat, Rylan Conway, Patrick Huber, Chinnadhurai Sankar, Ayushi Dalmia, Zechun Liu, Lemeng Wu, Tarek Elgamal, Adithya Sagar, Vikas Chandra, Raghuraman Krishnamoorthi. MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track). © 2026 Association for Computational Linguistics. CC BY 4.0. 10.18653/v1/2026.acl-industry.51. Original PDF, unmodified.

CC BY 4.0