Inference-time energy consumption

https://taxonomy.eticas.ai/risk/inference-energy-consumption

Maturity: emerging

High energy use during deployment and inference, increasing environmental impact and infrastructure costs.

This subcategory is emerging. It has not yet been validated through established assessment methods.

System type: ADM and LLM systems
Lifecycle stages: Post Processing

Mappings to external frameworks

Standards & frameworks

Framework Reference
NIST AI 600-1 — Generative AI Risk Profile Environmental Impacts (compute resource utilization in operation)

Taxonomies & vocabularies

Framework Reference
MIT AI Risk Repository Environmental harm (carbon and water footprints of inference)

Source: HRA project taxonomy