OvisOCR2: a promising 0.8B local document parser
Summary
OvisOCR2 is a new 0.8B end-to-end OCR model based on Qwen3.5-0.8B that converts full document pages directly into structured Markdown, including text, tables, formulas, and reading order. It achieves strong benchmark scores and is released under Apache 2.0 with vLLM support.
Similar Articles
OvisOCR2 Technical Report
OvisOCR2 is a 0.8B parameter end-to-end document parsing model that converts document page images to Markdown, achieving state-of-the-art scores on public benchmarks through a combination of supervised fine-tuning, reinforcement learning, and model fusion.
ATH-MaaS/OvisOCR2
OvisOCR2 is a compact 0.8B end-to-end model for page-level document parsing, achieving state-of-the-art performance on OmniDocBench and PureDocBench benchmarks.
OvisOCR2 (0.8B): first end-to-end model to top OmniDocBench - I threw 827 real scanned medical docs at it, here's everything I learned
OvisOCR2 is a 0.8B end-to-end document-parsing VLM that tops the OmniDocBench leaderboard, outperforming pipeline OCR systems on real-world scanned medical documents with higher accuracy and efficiency.
OvisOCR3 Technical Report
OvisOCR3 is a compact 0.8B vision-language model that unifies document parsing, general OCR, key information extraction, figure captioning, and cross-page table reconstruction via multi-teacher on-policy distillation and mixed-task reinforcement learning, achieving state-of-the-art results on benchmarks like OmniDocBench v1.6, OCRBench v2, and PureDocBench.
@poolmoon6: OCR is often needed. I use the one below, deployed locally. In real-world tests it outperforms Baidu OCR. On July 15, 2026, Alibaba released OvisOCR2. This is an end-to-end document parsing model based on Qwen3.5-0.8B, with only 0.8B parameters. On OmniDocBench v1…
Alibaba released OvisOCR2, an end-to-end document parsing model with 0.8B parameters based on Qwen3.5-0.8B, topping OmniDocBench v1.6 with a score of 96.58 — the first time an end-to-end approach has surpassed all pipeline-based approaches — and it is released under the Apache 2.0 license for commercial use.