All tasks / Models
MonkeyOCRv2-B-Parsing
Open-weights multilingual document-parsing model from the MonkeyOCR team, with CPU support and RAGFlow integration.
- zenosai (MonkeyOCR team)
- Open weights
- Released 14 Jul 2026
Where it ranks
- –Documents & OCRModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- zenosai (MonkeyOCR team)
- Family
- MonkeyOCR
- Released
- 14 Jul 2026
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 0.88B
- GPU memory to run locally
- ~3 GB (Estimate, no official figure: BF16 weights ≈ 0.88 B × 2 GB + ~1.5 GB runtime overhead. Size is the Hugging Face safetensors total.)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Price from huggingface.co, 19 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| MDPBench (multilingual document parsing) | 83.3% | MonkeyOCRv2-B-ParsingOverall (public split, page-level mean of text, formula and table scores) from the board's leaderboard.json (updated 2026-10-04). Best of two sizes (S-Parsing 82.5). MDPBench is maintained by the same research group as MonkeyOCR. | 4 Oct 2026 | huggingface.co |
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.
Earlier versions
- MonkeyOCR-pro-3B · —