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
    3
  • Partner Endpoint
    2
  • Download Available
    3
  • Code Generation
    0
  • Drug Discovery
    0
  • Retrieval Augmented Generation
    0
  • Image-to-Text
    0
  • Object Detection
    0
  • GMI Cloud
    2
  • Deep Infra
    1
  • Fireworks AI
    1
  • Together AI
    1
  • Bitdeer AI
    1
  • Qwen
    2
  • NVIDIA
    1
  • Mistral AI
    1
  • Microsoft
    1
  • University at Buffalo
    1
  • Enterprise
    0
  • NVIDIA BioNemo
    0
    • 6 models
    Mistral AI
    Downloadable

    mistral-small-4-119b-2603

    Hybrid MoE model unifying instruct, reasoning, and coding with multimodal input and 256k context
    chat
    847K
    1w
    Qwen
    Free Endpoint

    qwen3.5-122b-a10b

    122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
    chat
    3.51M
    2w
    Qwen
    Downloadable

    qwen3.5-397b-a17b

    Next-gen Qwen 3.5 VLM (400B MoE) brings advanced vision, chat, RAG, and agentic capabilities.
    chat
    12.25M
    1mo
    Microsoft
    Downloadable

    TRELLIS

    MSFT TRELLIS is a 3D AI model that generates high-quality 3D assets from text or image inputs.
    text-to-3d
    4.87K
    6mo
    NVIDIA
    Free Endpoint

    cosmos-nemotron-34b

    Multi-modal vision-language model that understands text/img/video and creates informative responses
    VLM
    8
    1y
    University at Buffalo
    Free Endpoint

    cached

    Context-aware chart extraction that can detect 18 classes for chart basic elements, excluding plot elements.
    nemo retriever
    192
    1y
    Items per page
    of 1 pages