**Jina-OCR-v1: Faster Document Parsing on Low-Budget GPU** > jina-ocr-v1 is a v

**Jina-OCR-v1: Faster Document Parsing on Low-Budget GPU**

> jina-ocr-v1 is a vision language model with 3.4B parameters and 570M active parameters, scoring 91.1 on OmniDocBench v1.6 and 83.4 on olmOCR-Bench. jinaai/jina-ocr-v1 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. jina-ocr-v1 - Search Foundation Models Page-to-Markdown document parser in one pass at 570M active parameters Search Foundation Mo...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-09-18 04:34（北京时间）
- **原文**：[打开原文](https://jina.ai/en-US/news/jina-ocr-v1-faster-document-parsing-on-low-budget-gpus)