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 (3)

  • Free Endpoint
    3
  • Partner Endpoint
    5
  • Download Available
    2
  • Retrieval Augmented Generation
    0
  • Drug Discovery
    0
  • Image-to-Text
    0
  • Code Generation
    0
  • Speech-to-Text
    0
  • Deep Infra
    4
  • GMI Cloud
    3
  • Bitdeer AI
    1
  • CoreWeave
    1
  • Lightning AI
    1
  • NVIDIA
    2
  • Moonshotai
    2
  • DeepSeek AI
    1
  • Meta
    0
  • Mistral AI
    0
  • A100 SXM4 80GB
    0
  • B200
    0
  • GB200
    0
  • GH200 144G HBM3e
    0
  • H100 80GB HBM3
    0
  • Reasoning
  • long context
  • long-context
    • 5 models
    NVIDIA
    Downloadable

    nemotron-3-super-120b-a12b

    Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
    MoE
    Items per page
    of 1 pages
    43.29M
    1mo
    DeepSeek AI
    Deprecation in 3dFree Endpoint

    deepseek-v3.2

    State-of-the-art 685B reasoning LLM with sparse attention, long context, and integrated agentic tools.
    long context
    8.24M
    4mo
    NVIDIA
    Downloadable

    nemotron-3-nano-30b-a3b

    Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more
    MoE
    9.35M
    4mo
    Moonshotai
    Deprecation in 11dFree Endpoint

    kimi-k2-thinking

    Open reasoning model with 256K context window, native INT4 quantization and enhanced tool use.
    Conversational
    2.94M
    4mo
    Moonshotai
    Deprecation in 4dFree Endpoint

    kimi-k2-instruct-0905

    Follow-on version of Kimi-K2-Instruct with longer context window and enhanced reasoning capabilities.
    long-context
    8.1M
    7mo