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

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
    4
  • Partner Endpoint
    4
  • Download Available
    4
  • Synthetic Data Generation
    1
  • Drug Discovery
    0
  • Image-to-Text
    0
  • Code Generation
    0
  • Retrieval Augmented Generation
    0
  • Deep Infra
    3
  • Bitdeer AI
    2
  • GMI Cloud
    2
  • Together AI
    1
  • CoreWeave
    0
  • Qwen
    2
  • NVIDIA
    1
  • Mistral AI
    1
  • Microsoft
    1
  • Meta
    0
  • B200
    1
  • GB200
    1
  • H100 80GB HBM3
    0
  • L40S
    0
  • A100 SXM4 80GB
    0
    • 5 models
    NVIDIA
    Free Endpoint

    cosmos3-nano

    Generates physics-aware videos from text prompts or an image prompt for physical AI development.
    autonomous vehicles
    Items per page
    of 1 pages
    372
    2d
    Mistral AI
    DownloadableFree Endpoint

    mistral-small-4-119b-2603

    Hybrid MoE model unifying instruct, reasoning, and coding with multimodal input and 256k context
    code generation
    18.55M
    2mo
    Qwen
    DownloadableFree Endpoint

    qwen3.5-122b-a10b

    122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
    B200
    9.92M
    2mo
    Qwen
    DownloadableFree Endpoint

    qwen3.5-397b-a17b

    Next-gen Qwen 3.5 VLM (400B MoE) brings advanced vision, chat, RAG, and agentic capabilities.
    MoE
    11.04M
    3mo
    Microsoft
    Downloadable

    TRELLIS

    MSFT TRELLIS is a 3D AI model that generates high-quality 3D assets from text or image inputs.
    text-to-3d
    4.2K
    9mo