NVIDIA
Explore
Models
Blueprints
GPUs
Docs
⌘KCtrl+K
Terms of Use
Privacy Policy
Your Privacy Choices
Contact

Copyright © 2026 NVIDIA Corporation

13 results for

Filters (2)

  • Free Endpoint
    4
  • Partner Endpoint
    8
  • Download Available
    9
  • Code Generation
    1
  • Together AI
    7
  • Deep Infra
    5
  • CoreWeave
    3
  • Digital Ocean
    3
  • GMI Cloud
    3
  • NVIDIA
    5
  • OpenAI
    2
  • Microsoft
    1
  • Qwen
    1
  • Mistral AI
    1
  • math
  • Reasoning
    • Marin
    DeprecatedFree Endpoint

    marin-8b-instruct

    State-of-the-art open model trained on open datasets, excelling in reasoning, math, and science.
    Model
    Reasoning
    147K
    10mo
    NVIDIA
    DeprecatedDownloadable

    llama-3.1-nemotron-nano-4b-v1.1

    State-of-the-art open model for reasoning, code, math, and tool calling - suitable for edge agents
    Model
    edge
    79.42K
    9mo
    NVIDIA
    Deprecation in 5dDownloadable

    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.
    Model
    math
    5.87M
    9mo
    NVIDIA
    Downloadable

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

    Leading reasoning and agentic AI accuracy model for PC and edge.
    Model
    math
    692K
    9mo
    Mistral AI
    Free Endpoint

    magistral-small-2506

    High performance reasoning model optimized for efficiency and edge deployment
    Model
    coding
    1.22M
    9mo
    Microsoft
    DeprecatedFree Endpoint

    phi-4-mini-flash-reasoning

    Lightweight reasoning model for applications in latency bound, memory/compute constrained environments
    Model
    edge
    160K
    9mo
    Sarvamai
    Downloadable

    sarvam-m

    Multilingual, hybrid-reasoning model optimized for Indian language tasks, programming, mathematical reasoning capabilities.
    Model
    coding
    154K
    8mo
    OpenAI
    Downloadable

    gpt-oss-120b

    Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
    Model
    reasoning
    39.68M
    8mo
    NVIDIA
    Downloadable

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

    High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
    Model
    math
    1.36M
    9mo
    NVIDIA
    Downloadable

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

    High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
    Model
    math
    2.63M
    8mo
    Qwen
    DeprecatedFree Endpoint

    qwq-32b

    Powerful reasoning model capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems.
    Model
    coding
    1.05M
    9mo
    Meta
    Downloadable

    llama-3.3-70b-instruct

    Advanced LLM for reasoning, math, general knowledge, and function calling
    Model
    Instruction following
    12.84M
    10mo
    OpenAI
    Downloadable

    gpt-oss-20b

    Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
    Model
    reasoning
    8.51M
    8mo
    Items per page
    of 1 pages