Local AI PDF & Text Summarizer
Extract selected pages from a text PDF, review the excerpt, and summarize it locally with an open-source model.
Select document text
Select up to 10 pages. Scanned pages need OCR first.
0 / 4,000 characters
Desktop recommended. GPU mode needs WebGPU with shader-f16 support. CPU mode is slower; keep this tab open.
Ready. No model downloads until you start.
Your result
Small local models can omit details or invent facts. Check names, numbers and claims against your original material.
Scope you can see
Choose a page range and review the extracted excerpt before generating. This tool summarizes up to 4,000 characters of visible text, not an entire long document. Tables and multi-column layouts may extract out of order. It does not provide reliable legal, medical or financial interpretation.
What happens to the PDF?
PDF.js extracts text locally. The selected excerpt is processed by SmolLM2-360M-Instruct in the browser. Your document is not uploaded by this tool. If extraction is empty, use the OCR tool first.