GreenBench: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source LLM Inference on Apple Silicon

• URL: http://arxiv.org/abs/2608.28667v1
• Date: Mon, 24 Aug 2026 04:46:26 GMT
• Title: GreenBench: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source LLM Inference on Apple Silicon
• Abstract summary: This paper presents GreenBench, a benchmarking framework that evaluates the energy efficiency, throughput, and carbon footprint of five open-source Large Language Models (LLMs)<n>We find that the Apple M4 Pro draws only 0.47 W of CPU+GPU package power during sustained inference, with total system power of 8-12 W.<n>Smaller models (3-3.8B) deliver 2.6-4.2x higher throughput and up to 62% less energy per token than larger models (7-9B)<n>We provide per-token energy at package and system levels with CO2 estimates for India and US grids.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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 LLM inference on Apple Silicon, with its unified memory architecture, remains unstudied. This paper presents GreenBench, a benchmarking framework that evaluates the energy efficiency, throughput, and carbon footprint of five open-source LLMs (3-9B parameters) across three NLP tasks on an Apple M4 Pro with 48 GB unified memory. Using macOS powermetrics for direct power measurement and Ollama's nanosecond-precision timing, we find that the M4 Pro draws only 0.47 W of CPU+GPU package power during sustained inference, with total system power of 8-12 W, achieving 30-40x better energy efficiency per token than datacenter GPUs in single-user deployment. Smaller models (3-3.8B) deliver 2.6-4.2x higher throughput and up to 62% less energy per token than larger models (7-9B). Pareto analysis identifies Qwen 2.5 (7B) as the optimal accuracy-efficiency trade-off at 57% MMLU and 59 tokens/s, while Llama 3.2 (3B) suits latency-critical applications at 175 tokens/s. We provide per-token energy at package and system levels with CO2 estimates for India and US grids.

Related papers

• Are Large Language Models Economically Viable for Industry Deployment? [15.537777029587366]
  Generative AI-powered by Large Language Models (LLMs) is increasingly deployed in industry across healthcare decision support, financial analytics, enterprise retrieval, and conversational automation.<n>Yet prevailing evaluation pipelines remain accuracy-centric, creating a Deployment-Evaluation Gap.
  arXiv  Detail & Related papers  (2026-04-21T11:25:22Z)
• Babbling Suppression: Making LLMs Greener One Token at a Time [46.879983975894135]
  Large Language Models (LLMs) are increasingly used in modern software development.<n>LLMs produce extraneous output, referred to as "babbling", which incurs additional cognitive, economic, and energy costs.<n>This work proposes a practical, model-agnostic approach to reduce unnecessary output without compromising solution accuracy.
  arXiv  Detail & Related papers  (2026-04-08T07:21:02Z)
• Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters [169.7981969517903]
  Step 3.5 Flash bridges frontier-level agentic intelligence and computational efficiency.<n>We focus on what matters most when building agents: sharp reasoning and fast, reliable execution.
  arXiv  Detail & Related papers  (2026-02-11T07:53:51Z)
• Towards Green AI: Decoding the Energy of LLM Inference in Software Development [46.879983975894135]
  AI-assisted tools are increasingly integrated into software development, but their reliance on large language models (LLMs) introduces substantial computational and energy costs.<n>We conduct a phase-level analysis of LLM inference energy consumption, distinguishing between the (1) prefill, where the model processes the input and builds internal representations, and (2) decoding, where output tokens are generated using the stored state.
  arXiv  Detail & Related papers  (2026-02-05T14:38:19Z)
• Green MLOps: Closed-Loop, Energy-Aware Inference with NVIDIA Triton, FastAPI, and Bio-Inspired Thresholding [0.0]
  Bio-inspired framework maps protein-folding energy basins to inference cost landscapes.<n>A request is admitted only when the expected utility-to-energy trade-off is favorable.<n>Results connect biophysical energy models to Green MLORTOps and offer a practical, auditable basis for closed-loop energy-aware inference in production.
  arXiv  Detail & Related papers  (2026-01-06T15:50:11Z)
• Energy Use of AI Inference: Efficiency Pathways and Test-Time Compute [4.8312457834136175]
  Non-production estimates and assumptions can overstate energy use by 4-20x.<n>We quantify achievable efficiency gains at the model, serving platform, and hardware levels.<n>We estimate the baseline daily energy use of a deployment serving 1 billion queries to be 0.8 GWh/day.
  arXiv  Detail & Related papers  (2025-09-24T15:32:01Z)
• Guidelines for the Quality Assessment of Energy-Aware NAS Benchmarks [26.441107070248016]
  Energy-aware benchmarking aims to make it possible for NAS to trade off model energy consumption against accuracy.<n>We analyse EA-HAS-Bench based on these principles and find that the choice of GPU measurement API has a large impact on the quality of results.
  arXiv  Detail & Related papers  (2025-05-21T15:16:41Z)
• EfficientLLM: Efficiency in Large Language Models [64.3537131208038]
  Large Language Models (LLMs) have driven significant progress, yet their growing counts and context windows incur prohibitive compute, energy, and monetary costs.<n>We introduce EfficientLLM, a novel benchmark and the first comprehensive empirical study evaluating efficiency techniques for LLMs at scale.
  arXiv  Detail & Related papers  (2025-05-20T02:27:08Z)
• How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference [0.0]
  This paper introduces a novel infrastructure-aware benchmarking framework for quantifying the environmental footprint of AI inference across 30 state-of-the-art models as deployed in commercial data centers.<n>Our results show that o3 and DeepSeek-R1 emerge as the most energy-intensive models, consuming over 33 Wh per long prompt, more than 70 times the consumption of GPT-4.1 nano, and that Claude-3.7 Sonnet ranks highest in eco-efficiency.<n>These findings illustrate a growing paradox: Although AI is becoming cheaper and faster, its global adoption drives disproportionate resource consumption.
  arXiv  Detail & Related papers  (2025-05-14T17:47:00Z)
• BitNet b1.58 2B4T Technical Report [118.78752947128682]
  We introduce BitNet b1.58 2B4T, the first open-source, native 1-bit Large Language Model (LLM) at the 2-billion parameter scale.<n>Trained on a corpus of 4 trillion tokens, the model has been rigorously evaluated across benchmarks covering language understanding, mathematical reasoning, coding proficiency, and conversational ability.
  arXiv  Detail & Related papers  (2025-04-16T17:51:43Z)
• MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs [55.95879347182669]
  MoE architecture is renowned for its ability to increase model capacity without a proportional increase in inference cost. MoE-Lightning introduces a novel CPU-GPU-I/O pipelining schedule, CGOPipe, with paged weights to achieve high resource utilization. MoE-Lightning can achieve up to 10.3x higher throughput than state-of-the-art offloading-enabled LLM inference systems for Mixtral 8x7B on a single T4 GPU (16GB)
  arXiv  Detail & Related papers  (2024-11-18T01:06:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.