Your toolkit for tracking, benchmarking, and optimizing resource usage of local LLMs.
Users lack the tools to measure the resource usage and energy impact of local LLMs. Without visibility into resource consumption, it's difficult to make informed decisions about model selection, optimization, and sustainable AI practices.
Get started with one command:
npx envirollm startUse the CLI directly or alongside the dashboards:
Track your system performance across setups. Monitor CPU, GPU, and memory usage in real-time and get generic recommendations.
Start MonitoringBenchmark local LLMs and compare performance. Test inference speed, resource usage, and energy efficiency across different models and prompts.
Benchmark ModelsTest models with custom or preset prompts. Compare energy consumption, speed, and quality across different models.
Visualize performance metrics and identify the best model for your specific use case.
Get automatic model recommendations based on your benchmarks.
