Purchase Priority Classifier

How Purchase Priority Classifier 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 sort a list of planned purchases by priority, using only what the text says about each one. Put each item in one of three groups: Need now (safety, health, work, school or a deadline stated in the text), Plan for (needed but not urgent), Can wait (wants and upgrades). Give a short reason for each that points at the words in the text. Do not judge the person's choices beyond that and do not suggest cheaper products or brands. This is not financial, tax or legal advice, so do not tell the user what they should do with their money. Do not do any arithmetic: copy every amount, date and percentage exactly as written, and never compute totals, differences, gaps, averages or percentages.

What it returns

• Priority per item: One entry per item, written exactly as 'item → Need now / Plan for / Can wait: reason'. Keep any price as written.
• Deadlines mentioned: Items with a date or event attached, with that date or event as written.
• Questions to ask yourself: Two or three questions that would settle the close calls.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Purchase list: replace cracked phone screen $189, concert tickets $240, winter tires $620 before snow trip, espresso machine upgrade $499, child school laptop charger $38.

Priority per item

cracked phone screen $189 → Need now: replacement for a cracked phone screen. concert tickets $240 → Can wait: a concert ticket is a want. winter tires $620 before snow trip → Need now: needed before a snow trip. espresso machine upgrade $499 → Can wait: an upgrade is a want. child school laptop charger $38 → Need now: related to school needs.

Deadlines mentioned

winter tires $620 before snow trip

Questions to ask yourself

What is the date of the snow trip? Is the child's school laptop charger required immediately? Is the concert ticket purchase urgent?

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

Limitations

• Small language models make mistakes: they can miss an item, merge two, or state something more confidently than the text supports. Check the result against your input before you rely on it.
• It needs WebGPU and about 8 GB of memory, so it is offered on desktops and laptops, not on phones and tablets. Devices that cannot run it get the keyword fallback, clearly labelled.
• Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.
• This is not financial, tax or legal advice. Confirm anything important against your own records and with a qualified professional.