LI

LightOnOCR 3 4B

LightonocrGGUF by richardyoungUpdated 2026-10-20
Download on Hugging Face
Parameters4.2B
Context256K
Layers32
Architectureqwen35
Smallest quant0.0 GB
Quick answer

LightOnOCR 3 4B needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 0.0 GB to 4.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

LightOnOCR 3 4B – lightweight OCR with vision and layout understanding

LightOnOCR 3 4B is a 4.2 billion‑parameter vision‑language model based on Qwen3.5. It performs end‑to‑end OCR, providing text, bounding boxes, image descriptions and chart tables. The model is released under Apache‑2.0 for research and commercial use.

Good at

  • OCR transcription
  • Layout‑aware extraction
  • Visual understanding of charts and images

Limits

  • No text‑only mode beyond transcription
  • Requires image input for vision features
  • No multilingual support listed

Best for

  • Digitizing scanned PDFs locally
  • Extracting tables and receipts
  • Generating structured data from documents

Who it’s for. Developers building document‑understanding pipelines who need a single model for OCR, layout, and visual features. The model is suitable for local inference with llama.cpp or Ollama.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ3_M2.2 GB 3.7 GB
Fits Get file →
IQ4_XS2.5 GB 4.1 GB
Fits Get file →
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q5_K_M3.1 GB 4.6 GB
Fits Get file →
Q6_K3.5 GB 5.0 GB
Fits Get file →
Q8_04.5 GB 6.1 GB
Fits Get file →

For 8 GB VRAM, use IQ4_XS (file size 2.51 GB, memory 4.1 GB). For 12 GB VRAM, Q4_K_M (2.71 GB, 4.3 GB) or Q5_K_M (3.07 GB, 4.6 GB) are good options. For 16 GB VRAM, Q6_K (3.46 GB, 5 GB) or Q8_0 (4.48 GB, 6.1 GB) provide higher fidelity.

What GPU do you need for LightOnOCR 3 4B?

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 IQ3_M (2.2 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.5 GB file, about 5.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).

Which LightOnOCR 3 4B quant should you choose?

Q4_K_M is the usual starting point for LightOnOCR 3 4B: it balances file size and quality well. Here it is a 2.7 GB file.

The Q8_0 file is 4.5 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

Architectureqwen35
Parameters4.2B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byrichardyoung
Licenseapache-2.0
Downloads (HF)1,890
Last updated2026-10-20

Frequently asked questions about LightOnOCR 3 4B

How much VRAM does LightOnOCR 3 4B need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 LightOnOCR 3 4B on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LightOnOCR 3 4B GGUF?

It depends on the quant: file is 0.0 GB, IQ3_M is 2.2 GB, IQ4_XS is 2.5 GB, Q4_K_M is 2.7 GB, Q5_K_M is 3.1 GB, Q6_K is 3.5 GB and 1 more.

What context length does LightOnOCR 3 4B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download LightOnOCR 3 4B GGUF?

The files are on Hugging Face in the richardyoung/LightOnOCR-3-4B-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 LightOnOCR 3 4B 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 LightOnOCR 3 4B on 8 GB VRAM?

Yes, the IQ4_XS quant uses about 4.1 GB of VRAM at 8 k context, which fits in 8 GB.

Does the model support text‑only inference?

The model is designed for vision tasks; text‑only inference is not supported beyond plain transcription.

Is the model licensed for commercial use?

Yes, it is released under the Apache‑2.0 license, allowing commercial deployment.

Other GGUFs of LightOnOCR-3-4B

Similar models

Browse all →

More from richardyoung

All by richardyoung →

More Lightonocr models

All Lightonocr →

Other small models

All small models →