SSyncDev

LightOnOCR-3-0.8B

SyncDev model directory · Profile updated Nov 17, 2026

Compare with another model

LightOnOCR-3-0.8B is LightOn's smallest open document model: page images in, markdown out, with optional bounding boxes and chart tables.

Key specifications

Specification score
9.8
License
Apache-2.0

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: Free open weights; a registry lists a hosted price of $2.464/1M input that was not checked.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Image input
  • Text input

Produces

  • Text output

Capabilities

VisionOpen weights

What is LightOnOCR-3-0.8B?

Send LightOnOCR-3-0.8B an empty prompt and a page image, and you get the whole page back as markdown. Send it the word "grounding" instead, and it adds labelled bounding boxes, short descriptions of embedded images, and chart data rendered as HTML tables. Two modes, one tiny model.

It is the smallest of LightOn's three LightOnOCR-3 document models, released on 8 October 2026 alongside 1B and 4B versions under Apache-2.0.

A different design from its siblings

The 0.8B is not just a shrunk 1B. It uses the Qwen3.5 vision-language architecture, while the 1B keeps the LightOnOCR-2 design. If you benchmarked the previous generation, this model may behave differently in ways that are not just about size.

How small is it? The launch materials call it 0.8B, the Hugging Face page shows 0.9B, and the safetensors total about 853M parameters. Any of those numbers means it runs on modest hardware.

Throughput

LightOn reports up to 4.78 pages per second on a single H100 with vLLM, when pages are rendered at 1540 pixels. Rendering resolution matters a lot here. Go much lower and small print suffers; go higher and throughput drops.

Item Detail
Hugging Face lightonai/LightOnOCR-3-0.8B
Parameters ~0.85B
Licence Apache-2.0
olmOCR-Bench 85.5
Long tiny-text category 94.1, the category leader
Thinking Trained and evaluated with it off
Transformers 5.2 or newer

Those benchmark scores are from LightOn's published results.

Unconfirmed limits

A registry lists a 262,144-token context and 16,384-token maximum output. Neither figure appears in LightOn's materials, so treat them as unverified. A page of dense text rarely approaches either limit anyway.

Do not turn thinking on

The model was trained and evaluated with thinking disabled. The Qwen3.5 base may expose a thinking switch, but enabling it puts the model outside what it was tuned for. Leave it off.

Building a fair test

Pull fifty real pages from your archive: scanned invoices, a two-column paper, a table that spans a page break, something with footnotes in 7-point type. Render at 1540 px, run both modes, and diff the markdown against a hand-checked version. Pay attention to table structure and reading order, the two places OCR models most often go wrong.

If 0.8B struggles, try the 4B sibling before switching vendors. For other options see document OCR models, compare with Mistral OCR 4.1, or browse the LightOn provider page.

How to evaluate LightOnOCR-3-0.8B

Compare the model on the work you need to complete.

Tasks and inputs

LightOnOCR-3-0.8B is listed for Image-text-to-text, Image-to-text, Document OCR. It accepts image, text and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.

Choosing a deployment

The weights are downloadable under Apache-2.0. Check runtime support and size the complete model and working context for your expected concurrency.

Frequently asked questions

With an empty prompt, the whole page as markdown. With a grounding prompt, it adds labelled bounding boxes, short image descriptions and chart data as HTML tables.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

OpenBMB

MiniCPM-OCR 1.0

MiniCPM-OCR 1.0 is OpenBMB's open 1.3B document-parsing model for text, tables, formulas and charts, with a free API and on-device apps.

— context

OpenBMB

MiniCPM-OCR Jev

MiniCPM-OCR Jev is OpenBMB's open 2B judge that scores whether an OCR result for a text, formula or table region is correct, from 0 to 1.

— context

Tencent

Youtu-Parsing-Omni

Youtu-Parsing-Omni is Tencent Youtu's 5B open parser that turns documents, charts, images, audio and video into one structured JSON format.

— context

Sarvam

Sarvam Vision 2.1

Sarvam Vision 2.1 is Sarvam's 3B document-intelligence VLM for OCR, tables, forms and Indic handwriting in 22 Indian languages plus English.

— context

NVIDIA

Nemotron 3.5 Parse

Nemotron 3.5 Parse is NVIDIA's 0.631B open document parser that turns page images into Markdown, HTML or JSON with tables, charts and reading order.

— context

Cohere

Cohere Parse

Cohere Parse (parse-v5.0) is a 2.3B vision-language document parser that turns PDFs, slides and scans into Markdown for RAG, at $1.50 per 1,000 pages.

8.19K context