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
    4
  • Partner Endpoint
    8
  • Download Available
    8
  • Code Generation
    1
  • Retrieval Augmented Generation
    0
  • Drug Discovery
    0
  • Image-to-Text
    0
  • Object Detection
    0
  • Together AI
    7
  • Deep Infra
    5
  • GMI Cloud
    3
  • CoreWeave
    3
  • Digital Ocean
    3
  • NVIDIA
    4
  • OpenAI
    2
  • Mistral AI
    1
  • Meta
    1
  • Microsoft
    1
  • Enterprise
    0
  • NVIDIA BioNemo
    0
  • math
    • 12 models
    OpenAI
    Downloadable

    gpt-oss-20b

    Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
    reasoning
    9.07M
    8mo
    OpenAI
    Downloadable

    gpt-oss-120b

    Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
    reasoning
    39.37M
    8mo
    NVIDIA
    Downloadable

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

    High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
    math
    2.81M
    8mo
    Sarvamai
    Downloadable

    sarvam-m

    Multilingual, hybrid-reasoning model optimized for Indian language tasks, programming, mathematical reasoning capabilities.
    coding
    165K
    8mo
    Microsoft
    DeprecatedFree Endpoint

    phi-4-mini-flash-reasoning

    Lightweight reasoning model for applications in latency bound, memory/compute constrained environments
    edge
    156K
    9mo
    Mistral AI
    Free Endpoint

    magistral-small-2506

    High performance reasoning model optimized for efficiency and edge deployment
    coding
    1.26M
    9mo
    Marin
    DeprecatedFree Endpoint

    marin-8b-instruct

    State-of-the-art open model trained on open datasets, excelling in reasoning, math, and science.
    Reasoning
    145K
    11mo
    NVIDIA
    Deprecation in 3dDownloadable

    llama-3.1-nemotron-ultra-253b-v1

    Superior inference efficiency with highest accuracy for scientific and complex math reasoning, coding, tool calling, and instruction following.
    math
    6.68M
    9mo
    Qwen
    DeprecatedFree Endpoint

    qwq-32b

    Powerful reasoning model capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems.
    coding
    931K
    9mo
    NVIDIA
    Downloadable

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

    High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
    math
    1.4M
    9mo
    NVIDIA
    Downloadable

    llama-3.1-nemotron-nano-8b-v1

    Leading reasoning and agentic AI accuracy model for PC and edge.
    math
    776K
    9mo
    Meta
    Downloadable

    llama-3.3-70b-instruct

    Advanced LLM for reasoning, math, general knowledge, and function calling
    Instruction following
    12.24M
    10mo
    Items per page
    of 1 pages