EnviroLLM: Resource Tracking and Optimization for Local AI

TL;DR

EnviroLLM is an open-source toolkit that enables users to monitor, benchmark, and optimize resource usage and environmental impact of local large language models across various platforms.

Contribution

It introduces a comprehensive system for real-time tracking, benchmarking, and personalized optimization of LLMs on personal devices, filling a gap in resource management tools.

Findings

Provides real-time resource monitoring and benchmarking.

Offers visualizations for longitudinal analysis.

Includes personalized model optimization recommendations.

Abstract

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.