nanonets/Nanonets-OCR2-3B
image-text-to-text model by nanonets
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Nanonets-OCR2: A model for transforming documents into structured markdown with intelligent content recognition and semantic tagging 🖥️ Live Demo | 📢 Blog | ⌨️ GitHub 📖 Cookbooks Nanonets-OCR2 by Nanonets is a family of powerful, state-of-the-art image-to-markdown OCR models that go far beyond traditional text extraction. It transforms documents into structured markdown…
Read the full model card ↗ · Preview checked 2026-11-15T07:08:35.623Z
Inside the original model card — Document outline
- Nanonets-OCR2 Family
- Usage
- Using transformers
- Using vLLM
- Using Docstrange
- Evaluation
- Markdown Evaluations
- Nanonets OCR2 Plus
- Nanonets OCR2 3B
- Visual Question Answering (VQA) Evaluations
- Tips to improve accuracy
- BibTex
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
nanonets/Nanonets-OCR2-3B is a image-text-to-text model repository published by nanonets on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 741,416
- Cumulative likes
- 518
- Hugging Face trending score
- 1
- Reported safetensors parameters
- 3,754,622,976
- Architecture
- Qwen2_5_VLForConditionalGeneration
- License
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2025-10-13T12:11:52.000Z
- Last modified
- 2025-10-16T09:56:02.000Z
Compatibility and lineage
Reported languages: multilingual
Reported base models: Qwen/Qwen2.5-VL-3B-Instruct
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-15T07:00:32.927Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.