LI

LightOnOCR-2-1B

LightonocrGGUF by MungertUpdated 2026-02-14
Download on Hugging Face
Parameters596M
Context16K
Layers28
Architectureqwen3
Smallest quant0.0 GB
Quick answer

LightOnOCR-2-1B needs about 1.8 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 31 quants, from 0.0 GB to 1.2 GB (F16).

LightOnOCR-2-1B – efficient OCR model with vision support

LightOnOCR-2-1B is a 0.596B parameter vision‑language model built on qwen3 architecture. It converts documents, PDFs, scans, and images into clean, naturally ordered text. The model is released under Apache‑2.0 license.

Good at

  • OCR of PDFs and scanned documents
  • Fast inference on GPUs
  • Supports LaTeX and multilingual text

Limits

  • No vision support in other variants
  • Requires 8k context for full capability
  • Large memory for higher precision quantizations

Best for

  • Document digitization
  • Receipt processing
  • Scientific article extraction

Who it’s for. Developers building OCR pipelines who need a lightweight, fast model. Researchers requiring a vision‑language model for document understanding can also use it.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.4 GB
Fits Get file →
IQ3_XXS0.3 GB 1.7 GB
Fits Get file →
IQ3_XS0.3 GB 1.7 GB
Fits Get file →
IQ3_M0.3 GB 1.8 GB
Fits Get file →
IQ3_S0.3 GB 1.8 GB
Fits Get file →
Q4_00.3 GB 1.8 GB
Fits Get file →
Q3_K_S0.3 GB 1.8 GB
Fits Get file →
Q3_K_M0.4 GB 1.8 GB
Fits Get file →
IQ4_XS0.4 GB 1.8 GB
Fits Get file →
Q4_10.4 GB 1.8 GB
Fits Get file →
IQ4_NL0.4 GB 1.8 GB
Fits Get file →
Q4_K_S0.4 GB 1.8 GB
Fits Get file →
Q4_K_M0.4 GB 1.8 GB
Fits Get file →
Q3_K_L0.4 GB 1.8 GB
Fits Get file →
Q5_00.4 GB 1.9 GB
Fits Get file →
Q4_00.4 GB 1.9 GB
Fits Get file →
Q4_K_L0.4 GB 1.9 GB
Fits Get file →
Q5_K_S0.4 GB 1.9 GB
Fits Get file →
Q4_10.4 GB 1.9 GB
Fits Get file →
Q5_K_M0.5 GB 1.9 GB
Fits Get file →
Q5_10.5 GB 1.9 GB
Fits Get file →
Q5_00.5 GB 1.9 GB
Fits Get file →
Q5_K_L0.5 GB 1.9 GB
Fits Get file →
Q6_K_M0.5 GB 1.9 GB
Fits Get file →
Q5_10.5 GB 1.9 GB
Fits Get file →
Q6_K_L0.5 GB 2.0 GB
Fits Get file →
Q8_00.6 GB 2.1 GB
Fits Get file →
BF161.0 GB 2.4 GB
Fits Get file →
F161.0 GB 2.4 GB
Fits Get file →
BF161.2 GB 2.6 GB
Fits Get file →
F161.2 GB 2.6 GB
Fits Get file →

For 8 GB VRAM, use IQ3_XXS or IQ3_XS (file size 0.3–0.31 GB, memory 1.7 GB). For 16 GB VRAM, Q4_0 or Q4_K_S (0.34–0.39 GB, memory 1.8 GB) provide a good balance of speed and accuracy. For 32 GB VRAM, Q8_0 (0.64 GB, memory 2.1 GB) gives the highest precision.

What GPU do you need for LightOnOCR-2-1B?

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 BF16 (1.2 GB file, about 2.6 GB in use).

Which LightOnOCR-2-1B quant should you choose?

Q4_K_M is the usual starting point for LightOnOCR-2-1B: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.6 GB, about 1.6 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

Architectureqwen3
Parameters596M
Layers28
Trained context16,384 tokens
KV cache (fp16)112 KB per token

Source

Quantized byMungert
Licenseapache-2.0
Downloads (HF)1,572
Last updated2026-02-14

Frequently asked questions about LightOnOCR-2-1B

How much VRAM does LightOnOCR-2-1B need?

About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.4 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-2-1B on an 8 GB GPU?

Yes, with BF16: the 1.2 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LightOnOCR-2-1B GGUF?

It depends on the quant: file is 0.0 GB, IQ3_XXS is 0.3 GB, IQ3_XS is 0.3 GB, IQ3_M is 0.3 GB, IQ3_S is 0.3 GB, Q4_0 is 0.3 GB and 25 more.

What context length does LightOnOCR-2-1B support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.9 GB at 8K and 1.9 GB at 16K.

Where can I download LightOnOCR-2-1B GGUF?

The files are on Hugging Face in the Mungert/LightOnOCR-2-1B-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-2-1B 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-2-1B on 8 GB VRAM?

Yes, use IQ3_XXS or IQ3_XS quantizations, which require about 1.7 GB of VRAM at 8k context.

Does the model support vision tasks?

Yes, the model has detected vision abilities and can process images and PDFs.

What license does the model use?

The model is released under Apache License 2.0.

Similar models

Browse all →

More from Mungert

All by Mungert →

More Lightonocr models

All Lightonocr →

Other tiny models

All tiny models →