NVIDIA
Explore
Models
Blueprints
GPUs
Docs
⌘KCtrl+K
Terms of Use
Privacy Policy
Your Privacy Choices
Contact

Copyright © 2026 NVIDIA Corporation

20 results for

Filters

  • Free Endpoint
    3
  • Partner Endpoint
    4
  • Download Available
    10
  • Launchable
    6
  • Enterprise
    2
  • Retrieval Augmented Generation
    11
  • Text-to-Embedding
    8
  • Image-to-Text
    2
  • Deep Infra
    4
  • Fireworks AI
    2
  • Together AI
    2
  • Bitdeer AI
    1
  • NVIDIA
    16
  • Meta
    2
  • Cyborg
    1
  • BAAI
    1
  • NVIDIA AI
    5
    • NVIDIA
    Free Endpoint

    rerank-qa-mistral-4b

    GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.
    Model
    Ranking
    296K
    1y
    BAAI
    Downloadable

    bge-m3

    Embedding model for text retrieval tasks, excelling in dense, multi-vector, and sparse retrieval.
    Model
    Embeddings
    3.18M
    11mo
    NVIDIA
    Launchable

    Biomedical AI-Q Research Agent Blueprint

    Build advanced AI agents within the biomedical domain using the AI-Q Blueprint and the BioNeMo Virtual Screening Blueprint
    Blueprint
    aiq
    1mo
    Cyborg
    Launchable

    Cyborg Enterprise RAG

    Securely extract, embed, and index multimodal data with encryption in-use for fast, accurate semantic search.
    Blueprint
    NIM
    1mo
    NVIDIA
    Launchable

    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
    1mo
    NVIDIA
    Launchable

    Retail Shopping Assistant

    Elevate Shopping Experiences Online and In Stores.
    Blueprint
    NVIDIA AI
    1mo
    NVIDIA
    Launchable

    Build an AI Virtual Assistant

    Create intelligent virtual assistants for customer service across every industry
    Blueprint
    NVIDIA AI
    1mo
    NVIDIA
    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
    1mo
    Meta
    Downloadable

    llama-3.2-11b-vision-instruct

    Cutting-edge vision-language model exceling in high-quality reasoning from images.
    Model
    chat
    1.08M
    9mo
    Meta
    Downloadable

    llama-3.2-90b-vision-instruct

    Cutting-edge vision-Language model exceling in high-quality reasoning from images.
    Model
    chat
    833K
    9mo
    NVIDIA
    Downloadable

    nv-embedqa-e5-v5

    English text embedding model for question-answering retrieval.
    Model
    Embedding
    6.77M
    8mo
    NVIDIA
    Downloadable

    llama-3.2-nemoretriever-1b-vlm-embed-v1

    Multimodal question-answer retrieval representing user queries as text and documents as images.
    Model
    nemo retriever
    390K
    9mo
    NVIDIA
    Downloadable

    llama-3.2-nv-rerankqa-1b-v2

    Fine-tuned reranking model for multilingual, cross-lingual text question-answering retrieval, with long context support.
    Model
    nemo retriever
    206K
    8mo
    NVIDIA
    Free Endpoint

    llama-3_2-nemoretriever-300m-embed-v1

    Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.
    Model
    Text-to-Embedding
    110K
    8mo
    NVIDIA
    Downloadable

    llama-3_2-nemoretriever-300m-embed-v2

    Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.
    Model
    Text-to-Embedding
    37.94K
    5mo
    NVIDIA
    Downloadable

    llama-nemotron-embed-1b-v2

    Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.
    Model
    Text-to-Embedding
    689K
    3w
    NVIDIA
    Downloadable

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

    Multimodal question-answer retrieval representing user queries as text and documents as images.
    Model
    nemo retriever
    2.85M
    1mo
    NVIDIA
    Enterprise

    Cosmos Dataset Search

    Accelerate post-training of end-to-end autonomous vehicle stacks with vector search and retrieval for large video datasets.
    Blueprint
    NVIDIA AI
    1mo
    NVIDIA
    Downloadable

    llama-3.2-nv-embedqa-1b-v2

    Multilingual and cross-lingual text question-answering retrieval with long context support and optimized data storage efficiency.
    Model
    nemo retriever
    6.2M
    8mo
    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
    215K
    10mo
    Items per page
    of 1 pages