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

Copyright © 2026 NVIDIA Corporation

25 results for

Filters

  • Free Endpoint
    1
  • Partner Endpoint
    2
  • Download Available
    17
  • Launchable
    6
  • Developer Example
    3
  • Enterprise Blueprint
    2
  • Object Detection
    6
  • Retrieval Augmented Generation
    6
  • Optical Character Recognition
    3
  • Text-to-Embedding
    3
  • Deep Infra
    2
  • NVIDIA
    23
  • Baidu
    1
  • Cyborg
    1
  • AI Engineer
    1
  • Data Engineer
    1
  • Developer
    1
  • NVIDIA AI
    5
  • AI And Machine Learning
    1
  • A100 PG509 200
    4
  • A100 SXM4 80GB
    4
  • A10G
    4
  • B200
    4
  • H100 80GB HBM3
    4
  • NeMo Retriever
    1

    • Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg` `.png` `.tiff`), Office (`.docx` `.pptx`), text (`.html` `.txt`), audio (`.mp3` `.wav` `.m4a`), or
    Skill
    Developer
    53
    1d
    NVIDIA
    Downloadable

    llama-nemotron-embed-1b-v2

    Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.
    Model
    Text-to-Embedding
    Items per page
    of 2 pages
    38.4M
    2mo
    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
    374K
    2mo
    NVIDIA
    Downloadable

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

    Multimodal question-answer retrieval representing user queries as text and documents as images.
    Model
    nemo retriever
    6.67M
    3mo
    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
    71.78K
    2mo
    NVIDIA
    Downloadable

    nemoretriever-ocr

    Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.
    Model
    Table Extraction
    11.78K
    10mo
    NVIDIA
    Downloadable

    nemoretriever-ocr-v1

    Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.
    Model
    Table Extraction
    1.15M
    9mo
    NVIDIA
    Downloadable

    nemotron-ocr-v1

    Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.
    Model
    Table Extraction
    372K
    2mo
    NVIDIA
    Downloadable

    nemoretriever-page-elements-v3

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Model
    Object Detection
    2.34K
    5mo
    NVIDIA
    Downloadable

    nemoretriever-parse

    Cutting-edge vision-language model exceling in retrieving text and metadata from images.
    Model
    optical character recognition
    91.42K
    1y
    NVIDIA
    Downloadable

    nemotron-graphic-elements-v1

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Model
    Object Detection
    38.89K
    2mo
    NVIDIA
    Downloadable

    nemotron-table-structure-v1

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Model
    Object Detection
    154K
    2mo
    NVIDIA
    DeprecatedDownloadable

    nemoretriever-graphic-elements-v1

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Model
    B200
    7.13K
    1y
    NVIDIA
    Downloadable

    nemoretriever-page-elements-v2

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Model
    B200
    268K
    1y
    NVIDIA
    DeprecatedDownloadable

    nemoretriever-table-structure-v1

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Model
    B200
    66.11K
    1y
    NVIDIA
    Free Endpoint

    nv-embedcode-7b-v1

    The NV-EmbedCode model is a 7B Mistral-based embedding model optimized for code retrieval, supporting text, code, and hybrid queries.
    Model
    nemo retriever
    330K
    1y
    Cyborg
    Launchable

    Cyborg Enterprise RAG

    Securely extract, embed, and index multimodal data with encryption in-use for fast, accurate semantic search.
    Blueprint
    NIM
    3mo
    NVIDIA
    Downloadable

    nv-embedqa-e5-v5

    English text embedding model for question-answering retrieval.
    Model
    Embedding
    28.5M
    10mo
    General
    LaunchableEnterprise

    Build an Enterprise RAG Pipeline Blueprint

    Power fast, accurate semantic search across multimodal enterprise data with NVIDIA’s RAG Blueprint—built on NeMo Retriever and Nemotron models—to connect your agents to trusted, authoritative sources of knowledge.
    Blueprint
    NVIDIA AI
    3mo
    Retail
    LaunchableDeveloper Example

    Multi-Agent Intelligent Warehouse

    An AI-powered, multi-agent system designed to optimize warehouse operations through intelligent automation, real-time monitoring, and natural language interaction.
    Blueprint
    NVIDIA AI
    3mo
    NVIDIA
    Downloadable

    nv-yolox-page-elements-v1

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Model
    Object Detection
    557
    10mo
    Retail
    LaunchableDeveloper Example

    Retail Shopping Assistant

    Elevate Shopping Experiences Online and In Stores.
    Blueprint
    NVIDIA AI
    3mo
    Media
    LaunchableDeveloper Example

    Streaming Data to RAG

    Sensor-captured radio enables real-time awareness, AI-driven analytics for actionable, searchable insights.
    Blueprint
    NVIDIA AI
    3mo
    Baidu
    Downloadable

    paddleocr

    Model for table extraction that receives an image as input, runs OCR on the image, and returns the text within the image and its bounding boxes.
    Model
    Optical Character Recognition
    1.27M
    10mo