lightonai/LightOnOCR-2-1B

Explore lightonai/LightOnOCR-2-1B: model specifications, capabilities, benchmark results, platform pricing and original sources.

huggingface/lightonai/LightOnOCR-2-1B

Specifications & capabilities

Published model ID
LightOnOCR-2-1B
Capabilities
multimodal, visionInput

Provider specifications & access

1–2 / 2

lightonai/LightOnOCR-2-1B ↗

source model id
HuggingFace/lightonai-lightonocr-2-1b@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    lightonai/LightOnOCR-2-1B ↗

    source model id
    publishers/hf-lightonai/models/lightonocr-2-1b@001
    hosting
    vertex-self-deployed
    platforms
    • Google Cloud Vertex AI
    architecture
    input_modalities
    • image
    • text
    output_modalities
    • text
    capabilities
    • multimodal
    • visionInput

    Original sources

    1–10 / 10

    Hugging Face · lightonai/LightOnOCR-2-1B ↗

    Google Cloud · Model page ↗

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    arXiv · Paper · 2412.13663 ↗

    arXiv · Paper · 2601.14251 ↗

    Google Cloud · Catalog ↗

    Hugging Face · Catalog ↗

    Hugging Face · Catalog ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–4 / 4

    Hugging Face model card

    1–1 / 1

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace