LI

LightOnOCR 3 0.8B

LightonocrGGUF by richardyoungUpdated 2026-10-20
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.0 GB
Quick answer

LightOnOCR 3 0.8B needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.0 GB to 0.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

LightOnOCR‑3 0.8B – lightest OCR model with vision and grounding

LightOnOCR‑3 0.8B is the smallest model in the LightOnOCR‑3 family, built on the Qwen3.5 vision‑language architecture. It provides transcription, grounding with labels and bounding boxes, and visual understanding such as image descriptions and chart data tables. The model is released under Apache 2.0 for research and commercial use.

Good at

  • Transcription with empty prompt
  • Grounding mode with labels and bounding boxes
  • Visual understanding of images and charts

Limits

  • No language list provided
  • No explicit context length limit beyond 262144 tokens
  • Vision projector only

Best for

  • Document transcription on local hardware
  • Grounding documents for layout extraction
  • Extracting chart data into tables

Who it’s for. Developers needing a lightweight OCR solution that runs locally with llama.cpp or Ollama. Ideal for projects that require transcription, layout analysis, and basic visual understanding without heavy GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.5 GB
Fits Get file →
Q8_00.8 GB 1.7 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (0.53 GB, 1.4 GB memory) is a good balance. If more VRAM is available, Q5_K_M or Q6_K (0.58–0.63 GB, 1.5 GB memory) offer slightly higher quality. The Q8_0 quant (0.81 GB, 1.7 GB memory) provides the best precision but needs the most memory.

What GPU do you need for LightOnOCR 3 0.8B?

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 Q8_0 (0.8 GB file, about 1.7 GB in use).

Which LightOnOCR 3 0.8B quant should you choose?

Q4_K_M is the usual starting point for LightOnOCR 3 0.8B: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.5 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
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byrichardyoung
Licenseapache-2.0
Downloads (HF)867
Last updated2026-10-20

Frequently asked questions about LightOnOCR 3 0.8B

How much VRAM does LightOnOCR 3 0.8B need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 0.8B on an 8 GB GPU?

Yes, with Q8_0: the 0.8 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LightOnOCR 3 0.8B GGUF?

It depends on the quant: file is 0.0 GB, Q4_K_M is 0.5 GB, Q5_K_M is 0.6 GB, Q6_K is 0.6 GB, Q8_0 is 0.8 GB.

What context length does LightOnOCR 3 0.8B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download LightOnOCR 3 0.8B GGUF?

The files are on Hugging Face in the richardyoung/LightOnOCR-3-0.8B-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 0.8B 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 0.8B on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 1.4 GB memory at 8k context, fitting comfortably in 8 GB VRAM.

Does this model support multiple languages?

The language list is empty; the model focuses on OCR and visual understanding rather than multilingual text.

Is vision support available in this GGUF quant?

Yes, the model includes a vision projector and supports grounding, image descriptions, and chart data extraction.

Other GGUFs of LightOnOCR-3-0.8B

Similar models

Browse all →

More from richardyoung

All by richardyoung →

More Lightonocr models

All Lightonocr →

Other tiny models

All tiny models →