How Much Does It Actually Cost to Run a Local LLM? (Euros per Million Tokens, Measured)

A detailed analysis on Towards Data Science examines the actual GPU electricity costs for running eight local LLM models using an RTX 3090. The measurements, calculated in Euros per million tokens, reveal that the cheapest model is not necessarily the smallest, nor is the most expensive one the largest. Separately, other reports investigate the financial requirements and overall costs associated with raising a child within various cities located across the state of Illinois.