@inproceedings{mohammad-etal-2026-large,
title = "Are Large Language Models Economically Viable for Industry Deployment?",
author = "Mohammad, Abdullah and
Ray, Sushant Kumar and
Arora, Pushkar and
Ali, Rafiq and
Shabbir, Ebad and
Kashyap, Gautam Siddharth and
Gao, Jiechao and
Naseem, Usman",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 6: Industry Track)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.106/",
doi = "10.18653/v1/2026.acl-industry.106",
pages = "1533--1540",
ISBN = "979-8-89176-394-4",
abstract = "Generative AI{---}powered by Large Language Models (LLMs){---}is increasingly deployed in industry across healthcare decision support, financial analytics, enterprise retrieval, and conversational automation, where reliability, efficiency, and cost control are critical. In such settings, models must satisfy strict constraints on energy, latency, and hardware utilization{---}not accuracy alone. Yet prevailing evaluation pipelines remain accuracy-centric, creating a Deployment{--}Evaluation Gap{---}the absence of operational and economic criteria in model assessment. To address this gap, we present EDGE-EVAL{---}a industry-oriented benchmarking framework that evaluates LLMs across their full lifecycle on legacy NVIDIA Tesla T4 GPUs. Benchmarking LLaMA and Qwen variants across three industrial tasks, we introduce five deployment metrics{---}Economic Break-Even (Nbreak), Intelligence-Per-Watt (IP W ), System Density ({\ensuremath{\rho}}sys), Cold-Start Tax (Ctax), and Quantization Fidelity (Qret){---}capturing profitability, energy efficiency, hardware scaling, serverless feasibility, and compression safety. Our results reveal a clear efficiency frontier{---}models in the {\ensuremath{<}} 2B parameter class dominate larger baselines across economic and ecological dimensions. LLaMA-3.2-1B (INT4) achieves ROI break-even in 14 requests (median), delivers 3{\texttimes} higher energy-normalized intelligence than 7B models, and exceeds 6,900 tokens/s/GB under 4-bit quantization. We further uncover an efficiency anomaly{---}while QLoRA reduces memory footprint, it increases adaptation energy by up to 7{\texttimes} for small models{---}challenging prevailing assumptions about quantization-aware training in edge deployment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohammad-etal-2026-large">
<titleInfo>
<title>Are Large Language Models Economically Viable for Industry Deployment?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sushant</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Ray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushkar</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafiq</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ebad</namePart>
<namePart type="family">Shabbir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gautam</namePart>
<namePart type="given">Siddharth</namePart>
<namePart type="family">Kashyap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiechao</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Usman</namePart>
<namePart type="family">Naseem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Generative AI—powered by Large Language Models (LLMs)—is increasingly deployed in industry across healthcare decision support, financial analytics, enterprise retrieval, and conversational automation, where reliability, efficiency, and cost control are critical. In such settings, models must satisfy strict constraints on energy, latency, and hardware utilization—not accuracy alone. Yet prevailing evaluation pipelines remain accuracy-centric, creating a Deployment–Evaluation Gap—the absence of operational and economic criteria in model assessment. To address this gap, we present EDGE-EVAL—a industry-oriented benchmarking framework that evaluates LLMs across their full lifecycle on legacy NVIDIA Tesla T4 GPUs. Benchmarking LLaMA and Qwen variants across three industrial tasks, we introduce five deployment metrics—Economic Break-Even (Nbreak), Intelligence-Per-Watt (IP W ), System Density (\ensuremathρsys), Cold-Start Tax (Ctax), and Quantization Fidelity (Qret)—capturing profitability, energy efficiency, hardware scaling, serverless feasibility, and compression safety. Our results reveal a clear efficiency frontier—models in the \ensuremath< 2B parameter class dominate larger baselines across economic and ecological dimensions. LLaMA-3.2-1B (INT4) achieves ROI break-even in 14 requests (median), delivers 3× higher energy-normalized intelligence than 7B models, and exceeds 6,900 tokens/s/GB under 4-bit quantization. We further uncover an efficiency anomaly—while QLoRA reduces memory footprint, it increases adaptation energy by up to 7× for small models—challenging prevailing assumptions about quantization-aware training in edge deployment.</abstract>
<identifier type="citekey">mohammad-etal-2026-large</identifier>
<identifier type="doi">10.18653/v1/2026.acl-industry.106</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.106/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1533</start>
<end>1540</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Are Large Language Models Economically Viable for Industry Deployment?
%A Mohammad, Abdullah
%A Ray, Sushant Kumar
%A Arora, Pushkar
%A Ali, Rafiq
%A Shabbir, Ebad
%A Kashyap, Gautam Siddharth
%A Gao, Jiechao
%A Naseem, Usman
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F mohammad-etal-2026-large
%X Generative AI—powered by Large Language Models (LLMs)—is increasingly deployed in industry across healthcare decision support, financial analytics, enterprise retrieval, and conversational automation, where reliability, efficiency, and cost control are critical. In such settings, models must satisfy strict constraints on energy, latency, and hardware utilization—not accuracy alone. Yet prevailing evaluation pipelines remain accuracy-centric, creating a Deployment–Evaluation Gap—the absence of operational and economic criteria in model assessment. To address this gap, we present EDGE-EVAL—a industry-oriented benchmarking framework that evaluates LLMs across their full lifecycle on legacy NVIDIA Tesla T4 GPUs. Benchmarking LLaMA and Qwen variants across three industrial tasks, we introduce five deployment metrics—Economic Break-Even (Nbreak), Intelligence-Per-Watt (IP W ), System Density (\ensuremathρsys), Cold-Start Tax (Ctax), and Quantization Fidelity (Qret)—capturing profitability, energy efficiency, hardware scaling, serverless feasibility, and compression safety. Our results reveal a clear efficiency frontier—models in the \ensuremath< 2B parameter class dominate larger baselines across economic and ecological dimensions. LLaMA-3.2-1B (INT4) achieves ROI break-even in 14 requests (median), delivers 3× higher energy-normalized intelligence than 7B models, and exceeds 6,900 tokens/s/GB under 4-bit quantization. We further uncover an efficiency anomaly—while QLoRA reduces memory footprint, it increases adaptation energy by up to 7× for small models—challenging prevailing assumptions about quantization-aware training in edge deployment.
%R 10.18653/v1/2026.acl-industry.106
%U https://aclanthology.org/2026.acl-industry.106/
%U https://doi.org/10.18653/v1/2026.acl-industry.106
%P 1533-1540
Markdown (Informal)
[Are Large Language Models Economically Viable for Industry Deployment?](https://aclanthology.org/2026.acl-industry.106/) (Mohammad et al., ACL 2026)
ACL
- Abdullah Mohammad, Sushant Kumar Ray, Pushkar Arora, Rafiq Ali, Ebad Shabbir, Gautam Siddharth Kashyap, Jiechao Gao, and Usman Naseem. 2026. Are Large Language Models Economically Viable for Industry Deployment?. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), pages 1533–1540, San Diego, California, USA. Association for Computational Linguistics.