Nanonets-OCR-s-AIO-GGUF

Nanonets-OCR-s is a state-of-the-art image-to-markdown OCR model that transforms complex documents into structured markdown with intelligent content recognition and semantic tagging. It goes beyond simple text extraction by accurately recognizing LaTeX equations, images, signatures, watermarks, checkboxes, and complex tables, making the output highly suitable for downstream processing by Large Language Models (LLMs). Built on the Qwen2.5-VL-3B Visual-Language Model and trained on over 250,000 diverse pages—including research papers, legal and financial documents, healthcare forms, and more—the model excels in preserving document structure and semantic context. It supports intelligent tagging of visual elements and special components, enabling efficient document understanding and automation in academic, legal, healthcare, and corporate workflows.

Model Files

File Name Quant Type File Size
Nanonets-OCR-s.f16.gguf F16 6.18 GB
Nanonets-OCR-s.Q2_K.gguf Q2_K 1.27 GB
Nanonets-OCR-s.Q3_K_L.gguf Q3_K_L 1.71 GB
Nanonets-OCR-s.Q3_K_M.gguf Q3_K_M 1.59 GB
Nanonets-OCR-s.Q3_K_S.gguf Q3_K_S 1.45 GB
Nanonets-OCR-s.Q4_K_M.gguf Q4_K_M 1.93 GB
Nanonets-OCR-s.Q4_K_S.gguf Q4_K_S 1.83 GB
Nanonets-OCR-s.Q5_K_M.gguf Q5_K_M 2.22 GB
Nanonets-OCR-s.Q5_K_S.gguf Q5_K_S 2.17 GB
Nanonets-OCR-s.Q6_K.gguf Q6_K 2.54 GB
Nanonets-OCR-s.Q8_0.gguf Q8_0 3.29 GB
Nanonets-OCR-s.IQ4_XS.gguf IQ4_XS 1.75 GB
Nanonets-OCR-s.i1-IQ1_M.gguf i1-IQ1_M 850 MB
Nanonets-OCR-s.i1-IQ1_S.gguf i1-IQ1_S 791 MB
Nanonets-OCR-s.i1-IQ2_M.gguf i1-IQ2_M 1.14 GB
Nanonets-OCR-s.i1-IQ2_S.gguf i1-IQ2_S 1.06 GB
Nanonets-OCR-s.i1-IQ2_XS.gguf i1-IQ2_XS 1.03 GB
Nanonets-OCR-s.i1-IQ2_XXS.gguf i1-IQ2_XXS 948 MB
Nanonets-OCR-s.i1-IQ3_M.gguf i1-IQ3_M 1.49 GB
Nanonets-OCR-s.i1-IQ3_S.gguf i1-IQ3_S 1.46 GB
Nanonets-OCR-s.i1-IQ3_XS.gguf i1-IQ3_XS 1.39 GB
Nanonets-OCR-s.i1-IQ3_XXS.gguf i1-IQ3_XXS 1.28 GB
Nanonets-OCR-s.i1-IQ4_NL.gguf i1-IQ4_NL 1.83 GB
Nanonets-OCR-s.i1-IQ4_XS.gguf i1-IQ4_XS 1.74 GB
Nanonets-OCR-s.i1-Q2_K.gguf i1-Q2_K 1.27 GB
Nanonets-OCR-s.i1-Q2_K_S.gguf i1-Q2_K_S 1.2 GB
Nanonets-OCR-s.i1-Q3_K_L.gguf i1-Q3_K_L 1.71 GB
Nanonets-OCR-s.i1-Q3_K_M.gguf i1-Q3_K_M 1.59 GB
Nanonets-OCR-s.i1-Q3_K_S.gguf i1-Q3_K_S 1.45 GB
Nanonets-OCR-s.i1-Q4_0.gguf i1-Q4_0 1.83 GB
Nanonets-OCR-s.i1-Q4_1.gguf i1-Q4_1 2 GB
Nanonets-OCR-s.i1-Q4_K_M.gguf i1-Q4_K_M 1.93 GB
Nanonets-OCR-s.i1-Q4_K_S.gguf i1-Q4_K_S 1.83 GB
Nanonets-OCR-s.i1-Q5_K_M.gguf i1-Q5_K_M 2.22 GB
Nanonets-OCR-s.i1-Q5_K_S.gguf i1-Q5_K_S 2.17 GB
Nanonets-OCR-s.i1-Q6_K.gguf i1-Q6_K 2.54 GB
Nanonets-OCR-s.mmproj-Q8_0.gguf mmproj-Q8_0 845 MB
Nanonets-OCR-s.mmproj-f16.gguf mmproj-f16 1.34 GB
imatrix.dat imatrix 3.36 MB

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

Downloads last month
1,278
GGUF
Model size
3B params
Architecture
qwen2vl
Hardware compatibility
Log In to view the estimation

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for prithivMLmods/Nanonets-OCR-s-AIO-GGUF

Quantized
(22)
this model

Collection including prithivMLmods/Nanonets-OCR-s-AIO-GGUF