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 visual document parser with roughly 570M active parameters per token, built on DeepSeek-OCR, that converts PDFs, scans, tables, charts and invoices into Markdown. The model includes a built-in FastMTP speculative decoding head that drafts 3 tokens per step while keeping output lossless, scoring 91.14 on OmniDocBench v1.6 and 83.4 on olmOCR-Bench and parsing 2.57 pages per second on a single A100. Weights are available on Hugging Face under CC BY-NC 4.0, with hosted access through Jina Reader.

Jina AI has released jina-ocr-v1, a visual document parser that converts PDFs, scans, tables, charts and invoices into Markdown. The model has 3.4B total parameters, with about 570M active per token, and builds on DeepSeek-OCR. A built-in FastMTP speculative decoding head drafts 3 tokens per step while keeping output lossless. It scores 91.14 on OmniDocBench v1.6 and 83.4 on olmOCR-Bench, and parses 2.57 pages per second on 1 A100. Weights are on Hugging Face under CC BY-NC 4.0, with hosted access through Jina Reader. The post Jina AI Releases jina-ocr-v1: A 3.4B MoE Document Parser With Built-In Speculative Decoding for Low-Budget GPUs 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/ appeared first on MarkTechPost https://www.marktechpost.com .