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 | 83k | 1.1k |
| Forks | 6.8k | 117 |
| Language | Python | C++ |
| License | LicenseRef-MinerU-Open-Source-License | MIT |
| Last activity | today | 1 months ago |
| Topics | ocr, rag | ocr |
| Curated connections | 14 | 6 |
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. Licence is Apache-2.0 plus MinerU's own terms: commercial use is fine until you pass 100M MAU or US$20M monthly revenue, and online services must attribute.
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.