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

Copyright © 2026 NVIDIA Corporation

Models

Deploy and scale models on your GPU infrastructure of choice with NVIDIA NIM inference microservices

Optimized by NVIDIALaunch from Hugging FaceBeta

Filters

  • Free Endpoint
    6
  • Partner Endpoint
    5
  • Download Available
    9
  • Retrieval Augmented Generation
    5
  • Text-to-Embedding
    4
  • Speech-to-Text
    2
  • Image-to-Text
    1
  • Code Generation
    1
  • Together AI
    4
  • Deep Infra
    2
  • Bitdeer AI
    1
  • CoreWeave
    1
  • GMI Cloud
    0
  • NVIDIA
    9
  • Meta
    1
  • Mistral AI
    1
  • Microsoft
    1
  • OpenAI
    1
  • A100 SXM4 80GB
    0
  • B200
    0
  • GB200
    0
  • GH200 144G HBM3e
    0
  • H100 80GB HBM3
    0
    • 15 models
    Z.ai
    Free Endpoint

    glm-4.7

    GLM-4.7 is a multilingual agentic coding partner with stronger reasoning, tool use, and UI skills.
    Tool Calling
    Items per page
    of 1 pages
    5.5M
    1w
    NVIDIA
    Free Endpoint

    nemotron-3-content-safety

    Multilingual, multimodal model for detecting unsafe and toxic content.
    llm safety
    29.12K
    1w
    NVIDIA
    Downloadable

    llama-nemotron-embed-1b-v2

    Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.
    Text-to-Embedding
    2.01M
    1mo
    NVIDIA
    Free Endpoint

    llama-3.1-nemotron-safety-guard-8b-v3

    Leading multilingual content safety model for enhancing the safety and moderation capabilities of LLMs
    content moderation
    115K
    6mo
    NVIDIA
    Downloadable

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

    Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.
    Text-to-Embedding
    86
    6mo
    Sarvamai
    Downloadable

    sarvam-m

    Multilingual, hybrid-reasoning model optimized for Indian language tasks, programming, mathematical reasoning capabilities.
    coding
    144K
    9mo
    NVIDIA
    Free Endpoint

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

    Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.
    Text-to-Embedding
    313K
    9mo
    Mistral AI
    Deprecation in 12dFree Endpoint

    magistral-small-2506

    High performance reasoning model optimized for efficiency and edge deployment
    coding
    1.17M
    9mo
    NVIDIA
    Downloadable

    parakeet-1.1b-rnnt-multilingual-asr

    High accuracy and optimized performance for transcription in 25 languages
    Automatic Speech Recognition
    12.1K
    1y
    Meta
    Free Endpoint

    llama-4-maverick-17b-128e-instruct

    A general purpose multimodal, multilingual 128 MoE model with 17B parameters.
    language generation
    12.54M
    9mo
    NVIDIA
    Downloadable

    magpie-tts-multilingual

    Natural and expressive voices in multiple languages. For voice agents and brand ambassadors.
    TTS
    44.73K
    10mo
    Microsoft
    Downloadable

    phi-4-mini-instruct

    Lightweight multilingual LLM powering AI applications in latency bound, memory/compute constrained environments
    Chat
    532K
    11mo
    OpenAI
    Downloadable

    whisper-large-v3

    Robust Speech Recognition via Large-Scale Weak Supervision.
    ASR
    44.5K
    1y
    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.
    nemo retriever
    2.4M
    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.
    nemo retriever
    96.93K
    9mo