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
    17
  • Partner Endpoint
    31
  • Download Available
    25
  • Code Generation
    4
  • Image-to-Text
    1
  • Synthetic Data Generation
    1
  • Drug Discovery
    0
  • Retrieval Augmented Generation
    0
  • Deep Infra
    22
  • Fireworks AI
    22
  • Together AI
    20
  • GMI Cloud
    16
  • Bitdeer AI
    9
  • NVIDIA
    10
  • Mistral AI
    6
  • DeepSeek AI
    6
  • Moonshotai
    4
  • Qwen
    3
  • Enterprise
    0
  • NVIDIA BioNemo
    0
  • reasoning
    • 42 models
    Mistral AI
    Downloadable

    mistral-small-4-119b-2603

    Hybrid MoE model unifying instruct, reasoning, and coding with multimodal input and 256k context
    chat
    1.46M
    1w
    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
    16.67M
    2w
    Qwen
    Downloadable

    qwen3.5-122b-a10b

    122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
    chat
    4.42M
    2w
    Minimaxai
    Downloadable

    minimax-m2.5

    MiniMax M2.5 is a 230B-parameter text-to-text AI model excelling in coding, reasoning, and office tasks.
    reasoning
    8.25M
    3w
    Z.ai
    Downloadable

    glm-5

    GLM-5 744B MoE enables efficient reasoning for complex systems and long-horizon agentic tasks.
    MoE
    24.57M
    1mo
    Stepfun-ai
    Free Endpoint

    step-3.5-flash

    200B open-source reasoning engine with sparse MoE powering frontier agentic AI.
    chat
    9.09M
    1mo
    Moonshotai
    Downloadable

    kimi-k2.5

    1T multimodal MoE for high‑capacity video and image understanding with efficient inference.
    Multimodal
    33.42M
    1mo
    Z.ai
    Free Endpoint

    glm-4.7

    GLM-4.7 is a multilingual agentic coding partner with stronger reasoning, tool use, and UI skills.
    Tool Calling
    15.18M
    1mo
    NVIDIA
    Free Endpoint

    nemotron-content-safety-reasoning-4b

    A context‑aware safety model that applies reasoning to enforce domain‑specific policies.
    NeMo Guardrails
    577K
    2mo
    NVIDIA
    Downloadable

    cosmos-reason2-8b

    Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
    video understanding
    175K
    2mo
    DeepSeek AI
    Free Endpoint

    deepseek-v3.2

    State-of-the-art 685B reasoning LLM with sparse attention, long context, and integrated agentic tools.
    chat
    16.46M
    3mo
    NVIDIA
    Downloadable

    nemotron-3-nano-30b-a3b

    Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more
    chat
    13.41M
    3mo
    Mistral AI
    Free Endpoint

    devstral-2-123b-instruct-2512

    State-of-the-art open code model with deep reasoning, 256k context, and unmatched efficiency.
    coding
    6.1M
    3mo
    Moonshotai
    Free Endpoint

    kimi-k2-thinking

    Open reasoning model with 256K context window, native INT4 quantization and enhanced tool use.
    Conversational
    3.26M
    3mo
    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
    14.42M
    5mo
    Moonshotai
    Free Endpoint

    kimi-k2-instruct-0905

    Follow-on version of Kimi-K2-Instruct with longer context window and enhanced reasoning capabilities.
    long-context
    11.44M
    6mo
    Qwen
    Downloadable

    qwen3-next-80b-a3b-thinking

    80B parameter AI model with hybrid reasoning, MoE architecture, support for 119 languages.
    chat
    4.39M
    6mo
    ByteDance
    Free Endpoint

    seed-oss-36b-instruct

    ByteDance open-source LLM with long-context, reasoning, and agentic intelligence.
    chat
    3.65M
    6mo
    DeepSeek AI
    Free Endpoint

    deepseek-v3.1

    DeepSeek V3.1 Instruct is a hybrid AI model with fast reasoning, 128K context, and strong tool use.
    chat
    13.23M
    7mo
    NVIDIA
    Downloadable

    nvidia-nemotron-nano-9b-v2

    High‑efficiency LLM with hybrid Transformer‑Mamba design, excelling in reasoning and agentic tasks.
    chat
    742K
    7mo
    OpenAI
    Downloadable

    gpt-oss-20b

    Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
    reasoning
    9.23M
    7mo
    OpenAI
    Downloadable

    gpt-oss-120b

    Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
    reasoning
    44.58M
    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
    5.21M
    8mo
    Sarvamai
    Downloadable

    sarvam-m

    Multilingual, hybrid-reasoning model optimized for Indian language tasks, programming, mathematical reasoning capabilities.
    coding
    586K
    8mo
    Items per page
    of 2 pages