PulseAugur
中
实时 06:30:12
English(EN) GreenBench: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source LLM Inference on Apple Silicon

GreenBench论文揭示Apple Silicon在LLM推理方面的能源效率

作者 PulseAugur 编辑部 · [1 个来源] ·

一项新的研究论文介绍了一个名为GreenBench的框架，该框架旨在衡量在Apple Silicon上运行的开源大语言模型（LLM）的能源效率和碳足迹。研究发现，与数据中心GPU相比，苹果的M4 Pro芯片在单用户设置下进行LLM推理的能源效率显著更高。小型模型在每token吞吐量和能耗方面表现更好，其中Qwen 2.5和Llama 3.2根据准确性和速度被确定为不同用例的最佳选择。 AI

影响 强调了在消费级硬件上部署节能LLM的潜力，减少了某些应用对耗能数据中心GPU的依赖。

排序理由 一项研究论文，介绍了一个针对特定硬件平台上LLM能源效率的新基准测试。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

GreenBench论文揭示Apple Silicon在LLM推理方面的能源效率

本文如何被排名

Signal score
30 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
一项研究论文，介绍了一个针对特定硬件平台上LLM能源效率的新基准测试。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Rajeswari Kannan, Raj Firke, Shreya Bengle, Srushti Deshmukh ·

    GreenBench：在Apple Silicon上对开源大模型推理的能效和碳足迹进行基准测试

    arXiv:2608.28667v1 Announce Type: cross Abstract: The rapid proliferation of Large Language Models (LLMs) has raised concerns about their environmental impact during inference. While Green AI research has focused on datacenter GPUs and embedded platforms, the energy profile of LL…

相关实体

相关话题