Skip to main content
NVIDIA
Explore
Models
Skills
Blueprints
GPUs
Docs
Terms of Use
Privacy Policy
Your Privacy Choices
Contact

Copyright © 2026 NVIDIA Corporation

8 results for

Filters (1)

  • Free Endpoint
    0
  • Partner Endpoint
    2
  • Download Available
    8
  • Retrieval Augmented Generation
    4
  • Object Detection
    2
  • Optical Character Recognition
    2
  • Text-to-Embedding
    2
  • Image-to-Text
    0
  • Deepinfra
    2
  • OpenRouter
    0
  • Digital Ocean
    0
  • Lightning AI
    0
  • Together AI
    0
  • NVIDIA
    8
  • Mistral AI
    0
  • A100 SXM4 80GB
    0
  • A10G
    0
  • H100 80GB HBM3
    0
  • H100 NVL
    0
  • H200
    0
  • nemo retriever
    • NVIDIA
    Downloadable

    nemotron-ocr-v2

    Nemotron OCR v2 is a state-of-the-art multilingual text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images.
    Model
    Table Extraction
    Items per page
    of 1 pages
    338K
    21d
    NVIDIA
    Downloadable

    nemotron-graphic-elements-v1

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Model
    Object Detection
    40K
    4mo
    NVIDIA
    Downloadable

    nemotron-ocr-v1

    Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.
    Model
    Table Extraction
    341K
    4mo
    NVIDIA
    Downloadable

    nemotron-table-structure-v1

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Model
    Object Detection
    157K
    4mo
    NVIDIA
    Downloadable

    llama-nemotron-embed-1b-v2

    Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.
    Model
    Text-to-Embedding
    4M
    4mo
    NVIDIA
    Downloadable

    llama-nemotron-rerank-1b-v2

    GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.
    Model
    nemo retriever
    501K
    4mo
    NVIDIA
    Downloadable

    llama-nemotron-embed-vl-1b-v2

    Multimodal question-answer retrieval representing user queries as text and documents as images.
    Model
    nemo retriever
    8M
    5mo
    NVIDIA
    Downloadable

    llama-nemotron-rerank-vl-1b-v2

    GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.
    Model
    nemo retriever
    84K
    3mo