Summarize a PDF with on-device AIAI
Get the key points of a document from AI that runs in your browser. The file never uploads.
How to summarize a PDF privately
- 1
Add your PDF
Drop or select the PDF. Its text is read on your device; nothing is uploaded.
- 2
Pick a style
Choose key points, a short TL;DR, or a one-line teaser.
- 3
Summarize on your device
A model built into your browser writes the summary locally. The document never leaves your device.
Why summarize on your device?
AI summaries are now everywhere, but every mainstream one works by uploading your document to a server. For a contract, a report or anything sensitive, that is exactly what you are trying to avoid. Running the model inside your browser means you get the summary and the document never leaves your machine.
Frequently asked questions
Does this upload my PDF to an AI server?+
No. The summary is produced by a model that runs inside your browser, so the document text is never sent anywhere. There is no endpoint that accepts your file. The live "0 B uploaded" indicator on the page measures outbound data in real time, so you can watch that it stays at zero while you use it. Every other online AI summarizer uploads your file; this one does not.
Exactly which AI model runs, and with what settings?+
It depends on your browser. If your browser has WebGPU, the tool uses Qwen2.5-1.5B-Instruct: a 1.5-billion-parameter instruction model, 4-bit quantized (q4f16_1), with a 4,096-token context window, run through MLC web-llm on your GPU inside a Web Worker. If instead your browser has a ready built-in AI (for example Chrome desktop with Gemini Nano already provisioned), it uses that and needs no download from us. The page shows which one applies and its details before you start.
How is the model installed, and from where?+
For the WebGPU model, pressing Download fetches the weights (about 850 MB) from this site over your own connection, same-origin, never from a third party. Your browser stores them (via IndexedDB) and caches them, so it is a genuine one-time download. For the built-in path, your browser downloads and manages its own model. In both cases only model weights are fetched; your PDF is never part of the download.
Where is the Qwen model hosted, and is it from a trusted source?+
We host it ourselves. The weights (about 850 MB) sit in our own AWS S3 bucket and are served over HTTPS through our CloudFront CDN, same-origin with this site, so at the time you use it nothing is fetched from a third party. The model is Qwen2.5-1.5B-Instruct, an open-weights model released by Alibaba’s Qwen team under the Apache-2.0 license, in the standard MLC web-llm build; we serve those published weights as they are and do not modify them.
How is this kept secure, and what stops the model from sending my data anywhere?+
The whole page runs under a strict Content-Security-Policy. Its connect-src is limited to our own origin plus a couple of privacy-preserving analytics endpoints that carry only anonymous page-view pings and never any file data, and there is no endpoint anywhere that accepts your document. The model runs in a sandboxed Web Worker that is bound by that same policy, so even the model code has no server it could send your PDF to; its open-source web-llm runtime is served from our own site, and the weights load over HTTPS. Your PDF text is only ever handed to the local model in memory. The live "0 B uploaded" indicator measures the page’s outbound data so you can watch it stay at zero, and our code and infrastructure run automated security checks on every change.
Will it download the model every time? How do I know it is already installed?+
No. After the first download it is cached in your browser, and the page detects that: on your next visit the model card shows "Downloaded and ready on this browser" instead of a Download button, and summarizing starts immediately with no network. If you clear your browser storage, it downloads again the next time and the status updates accordingly.
Can I choose the model, and where is each one stored?+
Yes. The tool has a Model selector with Auto, Built-in (Gemini Nano), and Downloadable (Qwen), plus a "Check my system" button that shows whether your device supports each. Gemini Nano is downloaded and stored by your browser (once, reused across every site). The Qwen model is stored in your browser’s storage for this site (IndexedDB), about 850 MB, downloaded once from this site and cached, and shared with Ask PDF so it never downloads twice. For a full write-up of both models and when each runs, see the blog post linked on the tool.
When is Gemini Nano used versus the downloadable Qwen model?+
On Auto, the tool uses Gemini Nano when your browser already has it downloaded and ready (instant, no download), otherwise the Qwen model if your browser has WebGPU, otherwise it offers to download the built-in model. Since a ready built-in model is relatively rare and WebGPU is common, most people use Qwen. You can also force either one with the Model selector.
Does anything get sent while or after summarizing?+
No. Once the model is on your device, the summary is generated entirely in your browser with no network at all, during or after. The only network event the whole feature can cause is the one-time model download coming to you; your document never goes the other way.
What are the requirements, and does it work on phones?+
It needs a desktop or laptop. The downloadable model needs WebGPU (recent Chrome, Edge, or other WebGPU-capable browsers) and a GPU with enough memory (about 1.6 GB of VRAM); the built-in path needs a browser that ships on-device AI. Phones and tablets are not supported: the model is a 1.5-billion-parameter AI (about 850 MB) that a mobile GPU cannot run, and loading it can exhaust memory and crash the device, so the tool does not offer it there. If a device cannot run it, the tool says so and does nothing; it never falls back to uploading your file. Every other PDF tool here still works regardless.
Where is the model stored and how do I remove it?+
In your browser’s own storage for this site (IndexedDB / Cache), about 850 MB for the WebGPU model. It never leaves your machine. To remove it, clear site data for this site in your browser settings; the page will then offer the download again next time.
What about scanned PDFs?+
A scanned PDF has no selectable text, so there is nothing to summarize directly. Run OCR PDF first (also on-device) to add a text layer, then summarize the result.
Can I re-summarize the same PDF or change the style?+
Yes. After a summary you can change the style (key points, TL;DR, or teaser) and regenerate on the same document, or load a different one, all without re-downloading the model, which stays loaded for the session.
How long a document can it handle?+
The model has a 4,096-token context, so very long documents are summarized from their opening section, and the tool tells you when that happens. For a full-document summary of a long file, split it first and summarize the parts.
Common uses
Task-specific guides for the situations people reach for this tool for.