EnviroLLM: Resource Tracking and Optimization for Local AI
This addresses the need for tools to assess efficiency and environmental impact for users deploying LLMs locally, though it is incremental as it builds on existing monitoring and benchmarking concepts.
The paper tackles the problem of measuring resource usage and environmental impact for locally deployed large language models by introducing EnviroLLM, an open-source toolkit that tracks, benchmarks, and optimizes performance and energy consumption on personal devices, providing real-time monitoring and personalized recommendations.
Large language models (LLMs) are increasingly deployed locally for privacy and accessibility, yet users lack tools to measure their resource usage, environmental impact, and efficiency metrics. This paper presents EnviroLLM, an open-source toolkit for tracking, benchmarking, and optimizing performance and energy consumption when running LLMs on personal devices. The system provides real-time process monitoring, benchmarking across multiple platforms (Ollama, LM Studio, vLLM, and OpenAI-compatible APIs), persistent storage with visualizations for longitudinal analysis, and personalized model and optimization recommendations. The system includes LLM-as-judge evaluations alongside energy and speed metrics, enabling users to assess quality-efficiency tradeoffs when testing models with custom prompts.