---
title: "Jina AI releases compact OCR model for low-budget GPUs"
url: https://www.parallelquant.com/posts/jina-ai-releases-compact-ocr-model-for-low-budget-gpus-d86cb4
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/09/18/jina-ai-releases-jina-ocr-v1-a-3-4b-moe-document-parser-with-built-in-speculative-decoding-for-low-budget-gpus/
published: 2026-09-18T21:21:59.000Z
topics: ["open source", "products"]
publisher: "Parallel Quant"
---

# Jina AI releases compact OCR model for low-budget GPUs

*2026-09-18 · Source: [MarkTechPost](https://www.marktechpost.com/2026/09/18/jina-ai-releases-jina-ocr-v1-a-3-4b-moe-document-parser-with-built-in-speculative-decoding-for-low-budget-gpus/)*

Jina AI released jina-ocr-v1, a 3.4B-parameter mixture-of-experts document parser (about 570M active parameters per token) that converts PDFs, scans, tables and charts into Markdown. Built on DeepSeek-OCR with speculative decoding, it scores 91.14 on OmniDocBench v1.6 and 83.4 on olmOCR-Bench, processing 2.57 pages per second on one A100. Weights are on Hugging Face under CC BY-NC 4.0.

**Why it matters:** Document parsing is one of the most common practical AI workloads, and a small, efficient model that runs on modest hardware lowers the cost barrier for OCR pipelines that previously needed much larger models.

**Topics:** open source, products

---
Read the original: https://www.marktechpost.com/2026/09/18/jina-ai-releases-jina-ocr-v1-a-3-4b-moe-document-parser-with-built-in-speculative-decoding-for-low-budget-gpus/
Canonical: https://www.parallelquant.com/posts/jina-ai-releases-compact-ocr-model-for-low-budget-gpus-d86cb4
Published by Parallel Quant — https://www.parallelquant.com