NA

Nanonets OCR2 1.5B Exp

NanonetsGGUF by mradermacherUpdated 2025-12-08
Download on Hugging Face
Parameters982M
Context32K
Layers16
Architectureqwen2vl
Smallest quant0.0 GB
Quick answer

Nanonets OCR2 1.5B Exp needs about 1.3 GB of memory at Q4_K_M (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 0.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 0.5 GB.

Nanonets OCR2 1.5B Exp – Vision model for structured markdown extraction

Nanonets OCR2 1.5B Exp transforms documents into structured markdown with intelligent content recognition. It handles LaTeX equations, image descriptions, signatures, watermarks, checkboxes, tables, flow charts, and handwritten text. The model is trained on 32768 context tokens and licensed under apache-2.0.

Good at

  • LaTeX equation recognition
  • Image and signature extraction
  • Complex table conversion

Limits

  • No vision support in non‑mmproj files
  • Requires large VRAM for full context
  • No language list provided

Best for

  • Document digitization
  • Legal and business form processing
  • Academic paper conversion

Who it’s for. Developers building OCR pipelines that need structured markdown output. Researchers requiring detailed semantic tagging of documents. Companies automating legal and financial document workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.6 GB
Fits Get file →
IQ1_S0.3 GB 1.0 GB
Fits Get file →
IQ1_M0.3 GB 1.0 GB
Fits Get file →
IQ2_XXS0.4 GB 1.0 GB
Fits Get file →
IQ2_XS0.4 GB 1.0 GB
Fits Get file →
IQ2_S0.4 GB 1.0 GB
Fits Get file →
IQ2_M0.4 GB 1.0 GB
Fits Get file →
Q2_K_S0.5 GB 1.1 GB
Fits Get file →
IQ3_XXS0.5 GB 1.1 GB
Fits Get file →
Q2_K0.5 GB 1.1 GB
Fits Get file →
IQ3_XS0.5 GB 1.1 GB
Fits Get file →
Q3_K_S0.5 GB 1.2 GB
Fits Get file →
IQ3_S0.5 GB 1.2 GB
Fits Get file →
IQ3_M0.5 GB 1.2 GB
Fits Get file →
Q3_K_M0.6 GB 1.2 GB
Fits Get file →
Q3_K_L0.6 GB 1.2 GB
Fits Get file →
IQ4_XS0.6 GB 1.2 GB
Fits Get file →
IQ4_NL0.6 GB 1.3 GB
Fits Get file →
Q4_00.6 GB 1.3 GB
Fits Get file →
Q4_K_S0.6 GB 1.3 GB
Fits Get file →
Q4_K_M0.6 GB 1.3 GB
Fits Get file →
Q4_10.7 GB 1.3 GB
Fits Get file →
Q5_K_S0.7 GB 1.3 GB
Fits Get file →
Q5_K_M0.7 GB 1.4 GB
Fits Get file →
Q6_K0.8 GB 1.4 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.65 GB, 1.3 GB memory at 8k context). For 4 GB VRAM, choose IQ1_S (0.32 GB, 1 GB memory). For 2 GB VRAM, IQ2_XXS (0.36 GB, 1 GB memory) is the smallest available.

What GPU do you need for Nanonets OCR2 1.5B Exp?

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 (0.8 GB file, about 1.4 GB in use).

Which Nanonets OCR2 1.5B Exp quant should you choose?

Q4_K_M is the usual starting point for Nanonets OCR2 1.5B Exp: it balances file size and quality well. Here it is a 0.6 GB file.

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
Parameters982M
Layers16
Trained context32,768 tokens
KV cache (fp16)16 KB per token

Source

Quantized bymradermacher
FamilyNanonets
Licenseapache-2.0
Downloads (HF)550
Last updated2025-12-08

Frequently asked questions about Nanonets OCR2 1.5B Exp

How much VRAM does Nanonets OCR2 1.5B Exp need?

About 1.3 GB at Q4_K_M with an 8K context window. That is the 0.6 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 1.5B Exp on an 8 GB GPU?

Yes, with Q6_K: the 0.8 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nanonets OCR2 1.5B Exp GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB and 19 more.

What context length does Nanonets OCR2 1.5B Exp support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.5 GB at 32K.

Where can I download Nanonets OCR2 1.5B Exp GGUF?

The files are on Hugging Face in the mradermacher/Nanonets-OCR2-1.5B-exp-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Nanonets OCR2 1.5B Exp use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 1.3 GB memory at 8k context, which fits within 8 GB VRAM.

Does the model support multiple languages?

The model does not list supported languages; it focuses on document structure rather than language detection.

Is there a vision component?

Yes, the model is a vision model; mmproj files are available in the static repository.

Other GGUFs of Nanonets-OCR2-1.5B-exp

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nanonets models

All Nanonets →

Other tiny models

All tiny models →