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 (1)

  • Free Endpoint
    5
  • Partner Endpoint
    11
  • Download Available
    8
  • Code Generation
    2
  • Synthetic Data Generation
    1
  • Retrieval Augmented Generation
    0
  • Drug Discovery
    0
  • Image-to-Text
    0
  • Deep Infra
    8
  • Fireworks AI
    7
  • Together AI
    7
  • GMI Cloud
    4
  • CoreWeave
    3
  • NVIDIA
    5
  • Mistral AI
    2
  • Qwen
    2
  • OpenAI
    2
  • DeepSeek AI
    1
  • reasoning
    • 13 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
    chat
    4.86M
    1w
    Qwen
    Free Endpoint

    qwen3.5-122b-a10b

    122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
    chat
    2.06M
    2w
    NVIDIA
    Free Endpoint

    nemotron-content-safety-reasoning-4b

    A context‑aware safety model that applies reasoning to enforce domain‑specific policies.
    NeMo Guardrails
    567K
    1mo
    NVIDIA
    Downloadable

    cosmos-reason2-8b

    Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
    video understanding
    208K
    2mo
    DeepSeek AI
    Free Endpoint

    deepseek-v3.1-terminus

    DeepSeek-V3.1: hybrid inference LLM with Think/Non-Think modes, stronger agents, 128K context, strict function calling.
    chat
    12.52M
    5mo
    OpenAI
    Downloadable

    gpt-oss-20b

    Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
    reasoning
    8.4M
    7mo
    OpenAI
    Downloadable

    gpt-oss-120b

    Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
    reasoning
    37.86M
    7mo
    NVIDIA
    Downloadable

    llama-3.3-nemotron-super-49b-v1.5

    High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
    chat
    5.2M
    7mo
    Moonshotai
    Free Endpoint

    kimi-k2-instruct

    State-of-the-art open mixture-of-experts model with strong reasoning, coding, and agentic capabilities
    coding
    16.48M
    8mo
    Qwen
    Free Endpoint

    qwq-32b

    Powerful reasoning model capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems.
    coding
    4.38M
    8mo
    NVIDIA
    Downloadable

    llama-3.3-nemotron-super-49b-v1

    High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
    chat
    1.13M
    8mo
    Mistral AI
    Downloadable

    mixtral-8x22b-instruct-v0.1

    An MOE LLM that follows instructions, completes requests, and generates creative text.
    chat
    5.02M
    8mo
    Mistral AI
    Downloadable

    mixtral-8x7b-instruct-v0.1

    An MOE LLM that follows instructions, completes requests, and generates creative text.
    chat
    732K
    8mo
    Items per page
    of 1 pages