QW

Nanonets-OCR2-3B

QwenGGUF by MungertUpdated 2025-10-26
Download on Hugging Face
Parameters3.09B
Context125K
Layers36
Architectureqwen2vl
Smallest quant0.0 GB
Quick answer

Nanonets-OCR2-3B needs about 2.8 GB of memory at Q4_K_M (a 2.0 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 6.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

Nanonets-OCR2-3B – a 3.09B parameter vision‑language model

Nanonets-OCR2-3B is a 3.09B parameter model built on Qwen2.5‑VL‑3B‑Instruct. It supports image‑to‑text tasks and can process documents, forms, and invoices. The model is available in multiple GGUF quantizations.

Good at

  • Vision‑to‑text OCR
  • Structured document extraction
  • Multimodal inference

Limits

  • No vision support beyond image‑to‑text
  • Large context required for full document understanding
  • License not specified

Best for

  • OCR on scanned forms
  • Extracting tables from invoices
  • Generating structured JSON from documents

Who it’s for. Developers needing a lightweight vision‑language model for document processing. The model is suitable for edge deployments where memory is limited but OCR accuracy is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.8 GB
Fits Get file →
IQ2_XXS1.0 GB 1.8 GB
Fits Get file →
IQ2_XS1.1 GB 1.9 GB
Fits Get file →
IQ2_S1.1 GB 1.9 GB
Fits Get file →
Q2_K_S1.2 GB 2.0 GB
Fits Get file →
IQ2_M1.2 GB 2.0 GB
Fits Get file →
Q2_K_M1.2 GB 2.0 GB
Fits Get file →
IQ3_XXS1.4 GB 2.2 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 →
IQ3_M1.5 GB 2.3 GB
Fits Get file →
Q3_K_M1.6 GB 2.4 GB
Fits Get file →
IQ4_XS1.7 GB 2.5 GB
Fits Get file →
IQ4_NL1.7 GB 2.5 GB
Fits Get file →
Q4_K_S1.9 GB 2.7 GB
Fits Get file →
Q4_01.9 GB 2.7 GB
Fits Get file →
Q4_12.0 GB 2.8 GB
Fits Get file →
Q4_K_M2.0 GB 2.8 GB
Fits Get file →
Q5_02.2 GB 3.0 GB
Fits Get file →
Q5_K_M2.3 GB 3.1 GB
Fits Get file →
Q5_12.4 GB 3.2 GB
Fits Get file →
Q6_K_M2.6 GB 3.4 GB
Fits Get file →
Q8_03.3 GB 4.1 GB
Fits Get file →
F164.5 GB 5.3 GB
Fits Get file →
BF166.2 GB 7.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.98 GB file, 2.8 GB memory at 8k context). If 4 GB VRAM is available, choose IQ2_XS (1.11 GB file, 1.9 GB memory). For higher precision and more memory, Q5_K_M or Q8_0 can be used.

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_M (2.6 GB file, about 3.4 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (4.5 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (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 2.0 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 byMungert
FamilyQwen
Downloads (HF)683
Last updated2025-10-26

Frequently asked questions about Nanonets-OCR2-3B

How much VRAM does Nanonets-OCR2-3B need?

About 2.8 GB at Q4_K_M with an 8K context window. That is the 2.0 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 BF16: 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, IQ2_XXS is 1.0 GB, IQ2_XS is 1.1 GB, IQ2_S is 1.1 GB, Q2_K_S is 1.2 GB, IQ2_M is 1.2 GB and 19 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 Mungert/Nanonets-OCR2-3B-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, the Q4_K_M quantization requires about 2.8 GB memory at 8k context, which fits within 8 GB VRAM.

What is the smallest quantization available?

IQ2_XXS is the smallest, with a 1.03 GB file and 1.8 GB memory at 8k context.

Does the model support video input?

No, the model only supports image‑to‑text tasks; video processing is not included.

Other GGUFs of Qwen2.5-VL-3B-Instruct

Similar models

Browse all →

More from Mungert

All by Mungert →

More Qwen models

All Qwen →

Other tiny models

All tiny models →