Energy ToolsetHow Appliance Energy Hog Detector 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 Classify 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 review a list of home appliances and usage notes and flag the likely energy hogs, using only clues in the text: age, hours of use, always-on, resistance heating, extra fridges or freezers. Copy wattages, hours and years exactly as written. Do not calculate kWh or costs and do not recommend specific brands.
What it returns
- Likely energy hogs: Each appliance that looks costly to run, with the clue from the text in brackets.
- Probably efficient: Appliances the text suggests are new or efficient.
- Worth measuring: Appliances whose usage is unclear and worth checking with a plug-in meter.
- Quick wins: Low-effort changes the text points to, such as unplugging or using a timer.