PaddleOCR-VL alternatives
Models that cover what PaddleOCR-VL does, closest first. All of them take the same request, so trying one is a one-word change.
Small open-source OCR model from Z.ai with layout regions. MIT licensed.
Open-source vision model that compresses pages into few tokens.
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
Fast document OCR that returns clean Markdown with tables and embedded images.
Document parser built for RAG pipelines, with several quality tiers.
Dashed tags are things PaddleOCR-VL does not support. Model IDs: zai/glm-ocr, deepseek/deepseek-ocr, baidu/unlimited-ocr, opendatalab/mineru, mistral/mistral-ocr, llamaindex/llamaparse.