ELANA: A Simple Energy and Latency Analyzer for LLMs
Not on the map. Why?
Abstract (arXiv)
The latency and power consumption of large language models (LLMs) are major constraints when serving them across a wide spectrum of hardware platforms, from mobile edge devices to cloud GPU clusters. Benchmarking is crucial for optimizing efficiency in both model deployment and next-generation model development. To address this need, we open-source a simple profiling tool, ELANA, for evaluating LLMs. ELANA is designed as a lightweight, academic-friendly profiler for analyzing model size, key-value (KV) cache size, prefilling latency (Time-to-first-token, TTFT), generation latency (Time-per-output-token, TPOT), and end-to-end latency (Time-to-last-token, TTLT) of LLMs on both multi-GPU and edge GPU platforms. It supports all publicly available models on Hugging Face and offers a simple command-line interface, along with optional energy consumption logging. Moreover, ELANA is fully compatible with popular Hugging Face APIs and can be easily customized or adapted to compressed or low bit-width models, making it ideal for research on efficient LLMs or for small-scale proof-of-concept studies. We release the ELANA profiling tool at: https://github.com/enyac-group/Elana.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 18 references that are in the map. First posted on arXiv 7 Dec 2025.
Builds on
16 of 18 references.
References · 16
- 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
- 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
- 2024Qwen2.5-Coder Technical Reportcited by 1,203
- 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,141
- 2024SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compressioncited by 243
- 2024QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Servingcited by 208
- 2023From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inferencecited by 170
- 2025Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Modelscited by 100
- 2022Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Trainingcited by 79
- 2024MoDeGPT: Modular Decomposition for Large Language Model Compressioncited by 48
- 2025The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimizationcited by 33
- 2023Reducing Energy Bloat in Large Model Trainingcited by 22
4 more
- 2024MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AIcited by 16
- 2025Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Modelscited by 16
- 2025UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMscited by 6
- 2025Promoting Sustainable Web Agents: Benchmarking and Estimating Energy Consumption through Empirical and Theoretical Analysiscited by 3
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures
- 2026Energy Efficiency of Locally Deployed LLMs: A Preliminary Quantitative GPU Power Benchmark on Consumer Hardware
- 2024PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
- 2025WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving
- 2025EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model
- 2025LLaMCAT: Optimizing Large Language Model Inference with Cache Arbitration and Throttling
- 2025Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling
- 2026LLM-Emu: Native Runtime Emulation of LLM Inference via Profile-Driven Sampling