Meal Log Pattern Classifier

How Meal Log Pattern Classifier works

Press Load model once: your browser downloads Gemma 3 1B instruction-tuned (web build) (728 MB) 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 3 1B 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 read a meal log and describe the eating pattern it shows: when meals happened, gaps between them, what kinds of food appear, and what the person said about hunger. Describe the pattern neutrally, without judging foods as good or bad. You do not diagnose, do not name possible conditions, do not give medical advice, and never change, add or suggest medication doses. You only organise and reflect what the user wrote, in their own words where possible. Do not calculate anything; copy numbers exactly as written. Do not count calories or nutrients and do not prescribe a diet.

What it returns

• Meals and snacks: One entry per meal or snack, as 'time as written: food as written'.
• Pattern label: A short neutral label for the overall pattern, for example 'light morning, large late dinner' or 'regular three meals'.
• What stands out: Neutral observations taken from the log, such as long gaps, late eating, repeated foods or hunger notes.
• Things to track next: Things that are not in the log but would make the pattern clearer (for example portion sizes, drinks, how they felt).

Worked example

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

Meal log: coffee only for breakfast, chicken bowl at 1pm, chips at 4pm, late pasta dinner, 2 sodas, no vegetables, hungry again by 10pm.

Meals and snacks

coffee chicken bowl chips late pasta dinner 2 sodas no vegetables

Pattern label

irregular morning, late evening

What stands out

large gaps late eating repeated foods hunger notes

Things to track next

portion sizes drinks how they felt

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.

You can switch models in the tool. Also available: Gemma 4 E2B instruction-tuned (web build) (2.0 GB). The larger language model gives more thorough answers but is a bigger download and needs a stronger device.

Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms.

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 4 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 a medical device and does not give medical advice, a diagnosis or a treatment plan. Ask a qualified health professional about any symptom, medication or change to your routine.

Good uses

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