All tasks / Models
Nanonets-OCR2-3B
Nanonets' open-weights 3B vision-language model that converts document images to structured Markdown.
- Nanonets
- Open weights
- Released 13 Oct 2025
Where it ranks
- –Documents & OCRModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- Nanonets
- Family
- Nanonets-OCR
- Released
- 13 Oct 2025
- Weights
- Open: download and run it yourself
- Parameters
- 3.75B
- GPU memory to run locally
- ~9 GB (Estimate, no official figure: BF16 weights ≈ 3.75 B × 2 GB + ~1.5 GB runtime overhead.)
- Access
- Free (open weights)
- Last verified
- 18 Oct 2026
Price from huggingface.co, 18 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| MDPBench (multilingual document parsing) | 64.2% | Nanonets-OCR2-3BOverall (public split, page-level mean of text, formula and table scores) from the board's leaderboard.json (updated 2026-10-04). | 4 Oct 2026 | huggingface.co |
| OCR Arena | 1,470 | Nanonets2-3BElo read from the site's JSON endpoint https://www.ocrarena.ai/api/leaderboard; 1386 battles. | 18 Oct 2026 | ocrarena.ai |
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.
Earlier versions
- Nanonets-OCR-s · 10 Jun 2025