MODEL REFERENCE / PaddlePaddle

PaddlePaddle/PaddleOCR-VL

PaddleOCR-VL (0.9B) — compact vision-language model for document parsing, OCR, tables, formulas, charts

vLLMSGLangdense0.9B131,072 ctxvLLM 0.11.1+multimodal

02 / Configure

Configure serving

Choose engine, hardware and deployment options. The command updates as you go.

03 / Understand

Model notes and examples