Energy ToolsetHow Demand Charge Explainer works
Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Analyze locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.
Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.
Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.
The instruction the model gets
You explain an electricity demand charge in plain English. A demand charge bills the highest power draw (kW) in a period, not total energy (kWh). Copy the peak kW, rate, time and charge exactly as written. Name the loads the text says ran at the same time, and suggest ways to stagger them. Do not add, subtract, multiply, average or convert any numbers; copy every figure exactly as written.
What it returns
- What happened: Two plain sentences on what set the demand charge, using the text's figures.
- Figures on the bill: Peak kW, demand rate, charge amount and the time of the peak, as written.
- Loads running together: Appliances or equipment the text says were on at the peak.
- Ways to lower it: Specific ways to stagger or delay the loads named in the text.