Skip to main content

LightOnOCR-3 (Document OCR)

LightOnOCR-3 is LightOn's open-weight OCR model (Apache-2.0, released October 2026). It reads a page image and returns markdown. With grounding turned on, it also returns a label and a bounding box for every block, and renders tables and charts as HTML tables. OpenTryOn exposes it on the parse service, next to Nemotron Parse.

Fashion uses include size charts, spec and tech sheets, line sheets, invoices and care-label scans.

Registry idHow it runsNeeds
lightonocr-3-localIn-process Hugging Face TransformersGPU or Apple Silicon; transformers>=5.2, torch
lightonocr-3-vllmClient for a vLLM / SGLang server you runYour server; nothing heavy on the client

LightOn has no hosted API for LightOnOCR-3, and no third-party host serves it.

Variants​

--variantModelNotes
0.8b (default)lightonai/LightOnOCR-3-0.8BAbout 0.9B parameters, roughly 2 GB in BF16
4blightonai/LightOnOCR-3-4BLightOn's recommended quality tier

Both use the Qwen3.5 vision-language architecture. The 1B sibling keeps the older LightOnOCR-2 architecture and isn't wired here. LightOn reports 85.5 (0.8B) and 86.3 (4B) on olmOCR-Bench; these are vendor figures.

CLI​

# Markdown from one page image
opentryon parse --model lightonocr-3-local --image size_chart.png

# Labelled blocks with bounding boxes, pages 1-2 of a PDF, larger model
opentryon parse --model lightonocr-3-local --image tech_pack.pdf --pages 1-2 --grounding --variant 4b

# Against your own vLLM server
vllm serve lightonai/LightOnOCR-3-0.8B --trust-remote-code \
--default-chat-template-kwargs '{"enable_thinking": false}'
opentryon parse --model lightonocr-3-vllm --image size_chart.pdf --grounding
FlagMeaning
--image, -iPage image or PDF (path or URL)
--groundingAlso return labelled blocks with bounding boxes
--pagesPDF pages to read, e.g. 1-3,5 (default: all)
--max-tokensMax tokens per page (default 4096)
--variant, --model-id, --devicelightonocr-3-local only
--base-url, --served-modellightonocr-3-vllm only (defaults from LIGHTONOCR_BASE_URL, LIGHTONOCR_MODEL)

PDFs are rendered with pypdfium2 (pip install pypdfium2) so the longest side is 2048 px, LightOn's recommended setting.

Output​

The result is saved as JSON:

{
"model": "lightonai/LightOnOCR-3-0.8B",
"grounding": true,
"page_count": 2,
"markdown": "## Size guide\n\n<table>...</table>",
"blocks": [
{"page": 1, "label": "title", "bbox": [113, 608, 263, 623], "text": "## Size guide", "continues": false}
],
"pages": [{"page": 1, "markdown": "...", "blocks": ["..."], "raw": "..."}]
}
  • bbox is [x1, y1, x2, y2], normalised to 0–1000 on both axes, whatever the image size.
  • Labels include text, title, list, table, chart, image, caption, formula, code, header, footer and page_number.
  • continues: true marks a block that carries on from the previous one, for example across columns; markdown joins them.
  • Without --grounding, each page is plain markdown and blocks is empty.

Python​

from tryon.models.lightonocr import LightOnOCRLocalAdapter
from tryon.api.lighton import LightOnOCRServerAdapter

result = LightOnOCRLocalAdapter(variant="0.8b").parse_document("size_chart.pdf", grounding=True)
print(result["markdown"])

served = LightOnOCRServerAdapter(base_url="http://127.0.0.1:8000/v1")
print(served.parse_document("care_label.jpg")["markdown"])

Requirements​

lightonocr-3-local loads with Qwen3_5ForConditionalGeneration, which needs transformers>=5.2 (the model card was saved with 5.5.4). That's newer than the shared opentryon[local] pin, so use a separate environment if loading fails:

pip install "transformers>=5.5.4" torch pillow pypdfium2

See also: Nemotron Parse (hosted NIM OCR), DeepSeek-OCR.