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 (1)

  • Free Endpoint
    51
  • Partner Endpoint
    32
  • Download Available
    37
  • Image-to-Text
    9
  • Code Generation
    9
  • Synthetic Data Generation
    1
  • Digital Twin
    1
  • Drug Discovery
    0
  • Deep Infra
    24
  • Bitdeer AI
    13
  • GMI Cloud
    13
  • Together AI
    12
  • CoreWeave
    8
  • NVIDIA
    14
  • Meta
    8
  • Mistral AI
    6
  • Qwen
    4
  • Google
    4
  • B200
    19
  • H200
    19
  • H100 80GB HBM3
    17
  • L40S
    14
  • H100 NVL
    12
  • chat
    • 52 models
    NVIDIA
    DownloadableFree Endpoint

    nemotron-3-ultra-550b-a55b

    Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
    Agent
    Today
    Items per page
    of 3 pages
    Stepfun-ai
    DownloadableFree Endpoint

    step-3.7-flash

    A sparse MoE multimodal reasoning model good for enterprise, agentic and coding tasks.
    B200
    1.65M
    6d
    Moonshotai
    DownloadableFree Endpoint

    kimi-k2.6

    1T multimodal MoE for long-horizon coding, agentic tool use, and image/video understanding.
    B200
    5.92M
    1mo
    Mistral AI
    DownloadableFree Endpoint

    mistral-medium-3.5-128b

    A high performing model for text generation, coding and agentic use cases
    coding
    3.14M
    1mo
    NVIDIA
    DownloadableFree Endpoint

    nemotron-3-nano-omni-30b-a3b-reasoning

    Nemotron 3 Nano Omni is an omni-modal reasoning model that understands images, video, speech, text.
    Image-to-Text
    8.91M
    1mo
    DeepSeek AI
    DownloadableFree Endpoint

    deepseek-v4-flash

    DeepSeek V4 Flash is a 284B MoE model with 1M-token context optimized for fast coding and agents.
    B200
    13.22M
    1mo
    DeepSeek AI
    Downloadable

    deepseek-v4-pro

    DeepSeek V4 scales to 1M-token context windows with efficient MoE architecture for coding tasks.
    B200
    8.11M
    1mo
    Z.ai
    DownloadableFree Endpoint

    glm-5.1

    GLM-5.1 is a flagship LLM for agentic workflows, coding, and long-horizon reasoning tasks.
    B200
    25.15M
    1mo
    NVIDIA
    DownloadableFree Endpoint

    ising-calibration-1-35b-a3b

    Open VLM for quantum computer calibration chart understanding across a range of qubit modalities.
    Quantum
    328K
    1mo
    Minimaxai
    DownloadableFree Endpoint

    minimax-m2.7

    MiniMax M2.7 is a 230B-parameter text-to-text AI model excelling in coding, reasoning, and office tasks.
    B200
    13.49M
    1mo
    Google
    DownloadableFree Endpoint

    gemma-4-31b-it

    Dense 31B model delivering frontier reasoning for coding, agentic workflows, and fine-tuning.
    B200
    5.64M
    2mo
    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
    18.38M
    2mo
    NVIDIA
    Free Endpoint

    nemotron-voicechat

    Nemotron 3 Voicechat
    English
    2.13K
    2mo
    NVIDIA
    DownloadableFree Endpoint

    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
    57.73M
    2mo
    Qwen
    DownloadableFree Endpoint

    qwen3.5-122b-a10b

    122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
    B200
    9.5M
    3mo
    Qwen
    DownloadableFree Endpoint

    qwen3.5-397b-a17b

    Next-gen Qwen 3.5 VLM (400B MoE) brings advanced vision, chat, RAG, and agentic capabilities.
    MoE
    11.16M
    3mo
    Stepfun-ai
    Free Endpoint

    step-3.5-flash

    200B open-source reasoning engine with sparse MoE powering frontier agentic AI.
    Agentic
    11.53M
    4mo
    NVIDIA
    DownloadableFree Endpoint

    nemotron-3-nano-30b-a3b

    Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more
    MoE
    11.29M
    5mo
    Mistral AI
    Free Endpoint

    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
    3.33M
    6mo
    Mistral AI
    DownloadableFree Endpoint

    ministral-14b-instruct-2512

    A general purpose VLM ideal for chat and instruction based use cases
    language generation
    3.42M
    6mo
    NVIDIA
    DownloadableFree Endpoint

    nemotron-nano-12b-v2-vl

    Nemotron Nano 12B v2 VL enables multi-image and video understanding, along with visual Q&A and summarization capabilities.
    B200
    2.06M
    7mo
    Stockmark
    DownloadableFree Endpoint

    stockmark-2-100b-instruct

    Japanese-specialized large-language-model for enterprises to read and understand complex business documents.
    sovereign ai
    1.52M
    8mo
    Qwen
    DownloadableFree Endpoint

    qwen3-next-80b-a3b-instruct

    Qwen3-Next Instruct blends hybrid attention, sparse MoE, and stability boosts for ultra-long context AI.
    B200
    22.67M
    8mo
    ByteDance
    Free Endpoint

    seed-oss-36b-instruct

    ByteDance open-source LLM with long-context, reasoning, and agentic intelligence.
    thinking budget
    1.17M
    9mo