How Dimension Text Extractor 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 Extract 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 pull every measurement out of product or spec text. For each one, record what it measures (length, width, height, depth, diagonal, weight, volume, diameter, cable length and so on), the number exactly as written and the unit exactly as written. Do not convert units, round, or calculate volumes or totals. If a value is ambiguous (for example 18 x 12 x 9 without saying which number is the width), say so instead of guessing. Include every figure in the text, including weights, load limits and capacities.
What it returns
- Measurements: One per measurement, written as 'what it measures: number unit' with the number and unit exactly as written.
- Overall size: The overall dimensions exactly as written (for example '18 x 12 x 9 inches'), or empty.
- Units used: Each unit that appears, as written.
- Unclear values: Values whose meaning or unit is unclear, with why.