LI

LightOnOCR 3 4B

LightonocrGGUF by prithivMLmodsUpdated 2026-10-08
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant2.3 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 9 quants, from 2.3 GB (Q3_K_M) to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

LightOnOCR‑3‑4B: a 4B‑parameter vision‑language OCR model

LightOnOCR‑3‑4B is a 4 billion‑parameter OCR model built on the Qwen3.5‑4B architecture. It supports transcription, grounding, image description and chart data extraction. The model is released under Apache 2.0 and can be run with llama.cpp or vLLM.

Good at

  • High‑quality OCR transcription
  • Vision‑grounded layout extraction
  • Chart data table generation

Limits

  • No speculative decoding
  • Requires 8 k context for full features
  • No text‑only mode without image

Best for

  • OCR of complex documents
  • Document layout analysis
  • Extracting structured data from charts

Who it’s for. Researchers and developers needing a single model for OCR and visual understanding. The model is suitable for both academic and commercial use under Apache 2.0.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M2.3 GB 3.8 GB
Fits Get file →
Q3_K_L2.4 GB 4.0 GB
Fits Get file →
Q4_K_S2.6 GB 4.1 GB
Fits Get file →
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q5_K_S3.0 GB 4.6 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 →
BF168.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (≈4.3 GB memory at 8 k context). With 12 GB VRAM Q5_K_M or Q6_K are suitable. For 24 GB VRAM the Q8_0 or BF16 variants provide higher precision.

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 Q3_K_L (2.4 GB file, about 4.0 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).
  • 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 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 Q3_K_M at 2.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byprithivMLmods
Licenseapache-2.0
Downloads (HF)9,993
Last updated2026-10-08

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: Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, Q4_K_S is 2.6 GB, Q4_K_M is 2.7 GB, Q5_K_S is 3.0 GB, Q5_K_M is 3.1 GB and 3 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 prithivMLmods/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 Q4_K_M quantization requires about 4.3 GB of VRAM at 8 k context, which fits in 8 GB.

Does the model support text‑only inference?

No, the model requires an image input; it does not provide a pure text‑only mode.

What license applies to the model?

The model is released under the Apache 2.0 license, allowing research and commercial use.

Other GGUFs of LightOnOCR-3-4B

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

More Lightonocr models

All Lightonocr →

Other small models

All small models →