Skip to content

Lighton · OCR

Lightonocr 3 0.8b

LightonOCRLightOnOCR familyOpen weights. One of its sources says the weights are publicly available.
From Eurouter's listing:
LightOnOCR-3-0.8B is the smallest and fastest model in LightOn's open-weight LightOnOCR-3 family: an end-to-end OCR and document-understanding model (about 0.85B parameters, Qwen3.5 vision-language architecture) that converts documents into Markdown, with optional labelled bounding-box grounding, image descriptions and chart-to-table extraction.
Max context
262K
Listings
2
Providers
2

Evidence and sources

Sources: Scaleway API data docs, Models.dev data, EURouter dataPrimary data from Scaleway API from Models.dev: creator, family, variant, weights availability from EURouter: description
Tags from its sources:open-sourceocrdocument-analysisvisionlightweight

Advantages and trade-offs

Compared with 10 representative OCR models

Advantages

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Files
Text

Capabilities

Supported operations and provider-stated features

Vision

Listings

 Eurouterlightonocr-3-0.8bSource: EURouter data262K—
 ScalewayRegions: 🇫🇷 fr-parlightonocr-3-0.8bSources: Models.dev data, Scaleway Model as a Service, Scaleway API data docs262K$2.464$0.00

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

OCR

Other

Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works