Flashcard Difficulty Labeler

How Flashcard Difficulty Labeler 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 help a student sort flashcards by difficulty. For each card (one per line), label it Easy if it asks to recall one fact or definition, Medium if it asks to list several connected facts or explain a simple process, and Hard if it asks to apply a method, solve a problem, compare, or explain why. Judge by what the card asks the student to do, not by the subject. Do not answer the cards.

What it returns

• Difficulty per card: One entry per card, written exactly as 'card → Easy/Medium/Hard: short reason'.
• Hardest cards: The cards labelled Hard.
• Suggested study order: A short plan, such as easy cards first to build recall, then medium, then hard cards with worked practice.
• Cards to split: Cards that ask for too much at once, with how to split them into smaller cards.

Worked example

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

Photosynthesis: definition Krebs cycle: inputs and outputs Balance this redox equation: Fe + O2 -> Fe2O3 Explain why ATP stores usable cellular energy Mitochondria: what organelle makes most ATP?

Difficulty per card

Photosynthesis: definition → Easy: recall a definition Krebs cycle: inputs and outputs → Medium: list inputs and outputs Balance this redox equation: Fe + O2 -> Fe2O3 → Hard: apply balancing method Explain why ATP stores usable cellular energy → Hard: explain a concept Mitochondria: what organelle makes most ATP? → Easy: recall an organelle function

Hardest cards

Balance this redox equation: Fe + O2 -> Fe2O3 Explain why ATP stores usable cellular energy

Suggested study order

Easy cards first to build recall, then medium, then hard cards with worked practice.

Cards to split

Balance this redox equation: Fe + O2 -> Fe2O3 → Split into separate cards for balancing steps. Explain why ATP stores usable cellular energy → Split into cards focusing on different aspects of energy storage.

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.

Good uses

• Triage education and study notes before deeper review
• Prepare consistent labels for repeat workflows
• Reduce manual sorting on small batches
• Keep sensitive drafts in the browser preview