评估大模型工业部署的经济性，发现小模型更省钱高效。
Are Large Language Models Economically Viable for Industry Deployment?
- 提出全流程工业评估框架，包含能耗、延迟、硬件利用率等新指标。
- 1B参数模型在4位量化下14次请求即回本，能效比7B模型高3倍。
- 揭示微调导致能耗飙升的异常现象，挑战现有量化训练认知。
基于大语言模型（LLMs）的生成式AI正广泛应用于医疗决策支持、金融分析、企业检索和对话自动化等领域，这些场景对可靠性、效率和成本控制要求极高。然而，当前评估体系仍以准确率为唯一标准，忽视了能源消耗、响应延迟和硬件利用率等实际部署约束，造成“部署-评估鸿沟”。为此，我们提出EDGE-EVAL——一个面向工业场景的基准框架，在旧款NVIDIA Tesla T4 GPU上对LLaMA与Qwen系列模型进行全生命周期评估。针对三个工业任务，引入五项部署指标：经济盈亏平衡点（Nbreak）、每瓦智能度（IPW）、系统密度（ρsys）、冷启动税（Ctax）和量化保真度（Qret），分别衡量盈利性、能效、硬件扩展性、无服务器可行性及压缩安全性。结果表明，<2B参数规模模型在经济与生态维度全面超越大模型；其中LLaMA-3.2-1B（INT4）中位数仅需14次请求即可实现投资回报平衡，单位能耗下的智能度为7B模型的3倍，4位量化下吞吐量超6,900 tokens/s/GB。进一步发现效率异常：虽然QLoRA降低内存占用，但使小型模型的适配能耗最高提升7倍，挑战了量化感知训练在边缘部署中的普遍假设。
原文摘要 · Abstract (English)
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 (IPW ), System Density (\r{ho}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 <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 3x 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 7x for small models-challenging prevailing assumptions about quantization-aware training in edge deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。