Skip to main content
NVIDIA
Explore
Models
Skills
Blueprints
GPUs
Docs
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
    27
  • Partner Endpoint
    17
  • Download Available
    24
  • Code Generation
    2
  • Synthetic Data Generation
    2
  • Image-to-Text
    1
  • Drug Discovery
    0
  • Retrieval Augmented Generation
    0
  • Deepinfra
    15
  • Together AI
    12
  • GMI Cloud
    10
  • Bitdeer
    6
  • Lightning AI
    5
  • NVIDIA
    11
  • Mistral AI
    3
  • Google
    2
  • OpenAI
    2
  • Minimaxai
    2
  • B200
    9
  • H200
    9
  • H100 80GB HBM3
    7
  • L40S
    6
  • A100 SXM4 80GB
    5
  • Reasoning
    • 28 models
    Minimaxai
    Free Endpoint

    minimax-m3

    MiniMax M3 Preview is a multimodal MoE vision-language model with strong reasoning, coding, and tool-calling capabilities.
    coding
    Items per page
    of 2 pages
    136K
    1d
    Google
    DownloadableFree Endpoint

    diffusiongemma-26b-a4b-it

    Diffusion-based 26B parameter LLM enabling parallel token generation for real-time text apps
    diffusion-llm
    97.31K
    3d
    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
    7.73M
    9d
    NVIDIA
    DownloadableFree Endpoint

    cosmos3-nano-reasoner

    Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
    video understanding
    1.94K
    13d
    Moonshotai
    DownloadableFree Endpoint

    kimi-k2.6

    1T multimodal MoE for long-horizon coding, agentic tool use, and image/video understanding.
    Multimodal
    7.09M
    1mo
    Mistral AI
    DownloadableFree Endpoint

    mistral-medium-3.5-128b

    A high performing model for text generation, coding and agentic use cases
    coding
    3.76M
    1mo
    DeepSeek AI
    DownloadableFree Endpoint

    deepseek-v4-pro

    DeepSeek V4 scales to 1M-token context windows with efficient MoE architecture for coding tasks.
    Moe
    7.5M
    1mo
    Z.ai
    DownloadableFree Endpoint

    glm-5.1

    GLM-5.1 is a flagship LLM for agentic workflows, coding, and long-horizon reasoning tasks.
    Agentic AI
    27.59M
    1mo
    NVIDIA
    DownloadableFree Endpoint

    ising-calibration-1-35b-a3b

    Open VLM for quantum computer calibration chart understanding across a range of qubit modalities.
    Quantum
    332K
    2mo
    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.
    reasoning
    14.36M
    2mo
    Google
    DownloadableFree Endpoint

    gemma-4-31b-it

    Dense 31B model delivering frontier reasoning for coding, agentic workflows, and fine-tuning.
    reasoning
    5.49M
    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
    12.52M
    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
    60.41M
    3mo
    Qwen
    DownloadableFree Endpoint

    qwen3.5-122b-a10b

    122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
    tool calling
    10.33M
    3mo
    Stepfun-ai
    Free Endpoint

    step-3.5-flash

    200B open-source reasoning engine with sparse MoE powering frontier agentic AI.
    Agentic
    11.71M
    4mo
    NVIDIA
    Free Endpoint

    nemotron-content-safety-reasoning-4b

    A context‑aware safety model that applies reasoning to enforce domain‑specific policies.
    NeMo Guardrails
    145K
    4mo
    NVIDIA
    Downloadable

    cosmos-reason2-8b

    Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
    video understanding
    191K
    5mo
    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
    11.91M
    6mo
    ByteDance
    Free Endpoint

    seed-oss-36b-instruct

    ByteDance open-source LLM with long-context, reasoning, and agentic intelligence.
    thinking budget
    1.18M
    9mo
    NVIDIA
    DownloadableFree Endpoint

    nvidia-nemotron-nano-9b-v2

    High‑efficiency LLM with hybrid Transformer‑Mamba design, excelling in reasoning and agentic tasks.
    thinking budget
    988K
    9mo
    OpenAI
    DownloadableFree Endpoint

    gpt-oss-20b

    Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
    reasoning
    18.45M
    10mo
    OpenAI
    DownloadableFree Endpoint

    gpt-oss-120b

    Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
    reasoning
    57.12M
    10mo
    NVIDIA
    DownloadableFree Endpoint

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

    High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
    advanced reasoning
    3.17M
    10mo
    Sarvamai
    DownloadableFree Endpoint

    sarvam-m

    Multilingual, hybrid-reasoning model optimized for Indian language tasks, programming, mathematical reasoning capabilities.
    coding
    236K
    10mo