NA

Nanonets OCR2 3B

NanonetsGGUF by prithivMLmodsUpdated 2025-11-12
Download on Hugging Face
Parameters3.09B
Context125K
Layers36
Architectureqwen2vl
Smallest quant0.0 GB
Quick answer

Nanonets OCR2 3B needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 37 quants, from 0.0 GB to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

Nanonets OCR2 3B – multimodal OCR for structured markdown

Nanonets OCR2 3B is a 3.09 billion‑parameter model based on qwen2vl. It converts images into structured markdown, extracting tables, LaTeX equations, signatures, watermarks, and more. The model supports visual question answering and multilingual content.

Good at

  • Image‑to‑markdown conversion
  • Complex table and equation extraction
  • Multilingual document understanding

Limits

  • No vision support beyond image‑to‑markdown
  • Large context window requires high VRAM
  • License not specified

Best for

  • Automated document digitization
  • Legal and financial form processing
  • Research paper extraction

Who it’s for. Developers building document‑centric AI pipelines and enterprises needing structured data from scanned documents. The model is suitable for users with access to GPU resources that can handle its memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.8 GB
Fits Get file →
IQ1_S0.8 GB 1.6 GB
Fits Get file →
IQ1_M0.9 GB 1.7 GB
Fits Get file →
IQ2_XXS0.9 GB 1.8 GB
Fits Get file →
IQ2_XS1.0 GB 1.8 GB
Fits Get file →
IQ2_S1.1 GB 1.9 GB
Fits Get file →
IQ2_M1.1 GB 1.9 GB
Fits Get file →
Q2_K_S1.2 GB 2.0 GB
Fits Get file →
Q2_K1.3 GB 2.1 GB
Fits Get file →
Q2_K1.3 GB 2.1 GB
Fits Get file →
IQ3_XXS1.3 GB 2.1 GB
Fits Get file →
IQ3_XS1.4 GB 2.2 GB
Fits Get file →
Q3_K_S1.5 GB 2.3 GB
Fits Get file →
Q3_K_S1.5 GB 2.3 GB
Fits Get file →
IQ3_S1.5 GB 2.3 GB
Fits Get file →
IQ3_M1.5 GB 2.3 GB
Fits Get file →
Q3_K_M1.6 GB 2.4 GB
Fits Get file →
Q3_K_M1.6 GB 2.4 GB
Fits Get file →
Q3_K_L1.7 GB 2.5 GB
Fits Get file →
Q3_K_L1.7 GB 2.5 GB
Fits Get file →
IQ4_XS1.7 GB 2.5 GB
Fits Get file →
IQ4_XS1.8 GB 2.6 GB
Fits Get file →
IQ4_NL1.8 GB 2.6 GB
Fits Get file →
Q4_01.8 GB 2.6 GB
Fits Get file →
Q4_K_S1.8 GB 2.6 GB
Fits Get file →
Q4_K_S1.8 GB 2.6 GB
Fits Get file →
Q4_K_M1.9 GB 2.7 GB
Fits Get file →
Q4_K_M1.9 GB 2.7 GB
Fits Get file →
Q4_12.0 GB 2.8 GB
Fits Get file →
Q5_K_S2.2 GB 3.0 GB
Fits Get file →
Q5_K_S2.2 GB 3.0 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q6_K2.5 GB 3.3 GB
Fits Get file →
Q6_K2.5 GB 3.3 GB
Fits Get file →
Q8_03.3 GB 4.1 GB
Fits Get file →
F166.2 GB 7.0 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (0.79 GB file, ~1.6 GB memory). For 12 GB VRAM, IQ2_M (1.14 GB file, ~1.9 GB memory). For 16 GB VRAM, Q4_K_M (1.93 GB file, ~2.7 GB memory).

What GPU do you need for Nanonets OCR2 3B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q6_K (2.5 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 GB in use).

Which Nanonets OCR2 3B quant should you choose?

Q4_K_M is the usual starting point for Nanonets OCR2 3B: it balances file size and quality well. Here it is a 1.9 GB file.

The Q8_0 file is 3.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters3.09B
Layers36
Trained context128,000 tokens
KV cache (fp16)36 KB per token

Source

Quantized byprithivMLmods
FamilyNanonets
Downloads (HF)822
Last updated2025-11-12

Frequently asked questions about Nanonets OCR2 3B

How much VRAM does Nanonets OCR2 3B need?

About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Nanonets OCR2 3B on an 8 GB GPU?

Yes, with F16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nanonets OCR2 3B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.8 GB, IQ1_M is 0.9 GB, IQ2_XXS is 0.9 GB, IQ2_XS is 1.0 GB, IQ2_S is 1.1 GB and 31 more.

What context length does Nanonets OCR2 3B support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download Nanonets OCR2 3B GGUF?

The files are on Hugging Face in the prithivMLmods/Nanonets-OCR2-3B-AIO-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Nanonets OCR2 3B on 8 GB VRAM?

Yes, using the IQ1_S quantized file which requires about 1.6 GB VRAM at 8 k context.

Does the model support visual question answering?

Yes, it can answer questions directly if the answer is present in the document.

What is the context length of this model?

The model was trained with a 128000 token context window.

Other GGUFs of Nanonets-OCR2-3B

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

More Nanonets models

All Nanonets →

Other tiny models

All tiny models →