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

  • Download Available
    121
  • API Endpoint
    94
  • Code Generation
    28
  • Drug Discovery
    13
  • Image-to-Text
    13
  • Retrieval Augmented Generation
    13
  • Object Detection
    9
  • NVIDIA
    88
  • Meta
    15
  • Mistral AI
    13
  • Microsoft
    12
  • Google
    10
    • 214 models
    Qwen

    qwen3.5-122b-a10b

    122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
    tool calling
    1d
    NVIDIA

    nemotron-table-structure-v1

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Object Detection
    1
    2d
    NVIDIA

    nemotron-page-elements-v3

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Object Detection
    1
    2d
    NVIDIA

    nemotron-graphic-elements-v1

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Object Detection
    1
    2d
    NVIDIA

    llama-nemotron-embed-1b-v2

    Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.
    Retrieval Augmented Generation
    2
    2d
    NVIDIA

    gliner-pii

    GLiNER PII detects Personally Identifiable Information in text.
    PII Detection
    15.52K
    3d
    Minimaxai

    minimax-m2.5

    MiniMax M2.5 is a 230B-parameter text-to-text AI model excelling in coding, reasoning, and office tasks.
    coding
    1.8M
    1w
    NVIDIA

    cosmos-transfer2.5-2b

    Generates physics-aware video world states for physical AI development using text prompts and multiple spatial control inputs derived from real-world data or simulation.
    Synthetic Data Generation
    1w
    Qwen

    qwen3.5-397b-a17b

    Next-gen Qwen 3.5 VLM (400B MoE) brings advanced vision, chat, RAG, and agentic capabilities.
    MoE
    5.14M
    2w
    Z.ai

    glm5

    GLM-5 744B MoE enables efficient reasoning for complex systems and long-horizon agentic tasks.
    MoE
    5.86M
    2w
    NVIDIA

    llama-nemotron-embed-vl-1b-v2

    Multimodal question-answer retrieval representing user queries as text and documents as images.
    nemo retriever
    591K
    3w
    Minimaxai

    minimax-m2.1

    MiniMax M2.1 excels in multi-language coding, app/web dev, office AI, and agent integration
    Agentic
    8.1M
    1mo
    Stepfun-ai

    step-3.5-flash

    200B open-source reasoning engine with sparse MoE powering frontier agentic AI.
    Agentic
    6.67M
    1mo
    Moonshotai

    kimi-k2.5

    1T multimodal MoE for high‑capacity video and image understanding with efficient inference.
    Multimodal
    19.52M
    1mo
    Z.ai

    glm4.7

    GLM-4.7 is a multilingual agentic coding partner with stronger reasoning, tool use, and UI skills.
    Tool Calling
    17.55M
    1mo
    NVIDIA

    nemotron-content-safety-reasoning-4b

    A context‑aware safety model that applies reasoning to enforce domain‑specific policies.
    NeMo Guardrails
    441K
    1mo
    NVIDIA

    cosmos-reason2-8b

    Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
    video understanding
    186K
    2mo
    NVIDIA

    nemoretriever-page-elements-v3

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Object Detection
    687K
    2mo
    DeepSeek AI

    deepseek-v3.2

    State-of-the-art 685B reasoning LLM with sparse attention, long context, and integrated agentic tools.
    long context
    14.58M
    2mo
    NVIDIA

    nemotron-3-nano-30b-a3b

    Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more
    MoE
    11.1M
    2mo
    NVIDIA

    riva-translate-4b-instruct-v1_1

    Translation model in 12 languages with few-shots example prompts capability.
    nvidia nim
    437K
    2mo
    Mistral AI

    devstral-2-123b-instruct-2512

    State-of-the-art open code model with deep reasoning, 256k context, and unmatched efficiency.
    coding
    4.84M
    2mo
    Moonshotai

    kimi-k2-thinking

    Open reasoning model with 256K context window, native INT4 quantization and enhanced tool use.
    Conversational
    2.99M
    2mo
    Mistral AI

    mistral-large-3-675b-instruct-2512

    A state-of-the-art general purpose MoE VLM ideal for chat, agentic and instruction based use cases.
    language generation
    4.89M
    3mo
    Items per page
    ...
    of 9 pages