MinerU vs TurboOCR
Heavyweight document-to-markdown/JSON parser — PDFs plus Office (docx/pptx/xlsx) through layout analysis and OCR into LLM-ready output for RAG and agentic pipelines. 73k stars, self-hostable. — versus — GPU document parser in C++/TensorRT: PP-OCRv6 OCR, layout, tables and formulas to Markdown at 200-559 img/s on one GPU — no VLM, HTTP + gRPC, one-line Docker deploy.
Same job — documents to LLM-ready Markdown. MinerU is the heavyweight Python pipeline with Office support; TurboOCR trades breadth for 200+ img/s on one GPU.
| MinerU | TurboOCR | |
|---|---|---|
| Stars | 77k | 894 |
| Forks | 6.4k | 88 |
| Language | Python | C++ |
| License | NOASSERTION | MIT |
| Last activity | 6 days ago | 3 days ago |
| Topics | ocr, rag | ocr |
| Curated connections | 11 | 3 |
MinerU — the curator's take
The incumbent when document variety is the problem: beyond PDFs it handles Office formats, with mature layout analysis (reading order, tables, formulas) and a huge user base shaking out edge cases. NOT the lightest option — it's a full pipeline with model downloads and real hardware appetite; for a handful of clean PDFs a smaller tool is faster to stand up. Check the license (NOASSERTION on GitHub — AGPL-family, matters for commercial use).
TurboOCR — the curator's take
The throughput bet: a classic multi-stage pipeline on TensorRT instead of a VLM — ~20 pages/s structured parsing where VLM parsers run ~1. Sharp on forms and receipts. When NOT: Linux + NVIDIA Turing+ only (Metal/ROCm still cooking), first start compiles engines (up to an hour on older cards), and benchmarks are self-published on its own harness — for messy scans and handwriting a VLM parser may still out-read it.