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

Copyright © 2026 NVIDIA Corporation

62 results for

Filters (1)

  • Download Available
    33
  • API Endpoint
    29
  • Enterprise
    0
  • Launchable
    0
  • Code Generation
    16
  • Image-to-Text
    6
  • Synthetic Data Generation
    0
  • Meta
    9
  • Microsoft
    8
  • NVIDIA
    7
  • DeepSeek AI
    7
  • Mistral AI
    6
  • NVIDIA AI
    0
  • chat
    • Microsoft

    phi-4-mini-flash-reasoning

    Lightweight reasoning model for applications in latency bound, memory/compute constrained environments
    Model
    edge
    455K
    7mo
    Z.ai

    glm5

    GLM-5 744B MoE enables efficient reasoning for complex systems and long-horizon agentic tasks.
    Model
    MoE
    7.38M
    3w
    IBM

    granite-3.3-8b-instruct

    Small language model fine-tuned for improved reasoning, coding, and instruction-following
    Model
    coding
    165K
    8mo
    NVIDIA

    nvidia-nemotron-nano-9b-v2

    High‑efficiency LLM with hybrid Transformer‑Mamba design, excelling in reasoning and agentic tasks.
    Model
    thinking budget
    704K
    6mo
    Qwen

    qwen3-next-80b-a3b-thinking

    80B parameter AI model with hybrid reasoning, MoE architecture, support for 119 languages.
    Model
    Reasoning
    3.71M
    5mo
    Stepfun-ai

    step-3.5-flash

    200B open-source reasoning engine with sparse MoE powering frontier agentic AI.
    Model
    Agentic
    7.22M
    1mo
    Sarvamai

    sarvam-m

    Multilingual, hybrid-reasoning model optimized for Indian language tasks, programming, mathematical reasoning capabilities.
    Model
    coding
    461K
    7mo
    Qwen

    qwq-32b

    Powerful reasoning model capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems.
    Model
    coding
    3.81M
    8mo
    Mistral AI

    magistral-small-2506

    High performance reasoning model optimized for efficiency and edge deployment
    Model
    coding
    3.87M
    8mo
    DeepSeek AI

    deepseek-r1-distill-qwen-14b

    Distilled version of Qwen 2.5 14B using reasoning data generated by DeepSeek R1 for enhanced performance.
    Model
    coding
    1.96K4.21M
    9mo
    DeepSeek AI

    deepseek-r1-distill-qwen-32b

    Distilled version of Qwen 2.5 32B using reasoning data generated by DeepSeek R1 for enhanced performance.
    Model
    coding
    2.35K4.65M
    9mo
    DeepSeek AI

    deepseek-v3.2

    State-of-the-art 685B reasoning LLM with sparse attention, long context, and integrated agentic tools.
    Model
    long context
    15.34M
    2mo
    Mistral AI

    devstral-2-123b-instruct-2512

    State-of-the-art open code model with deep reasoning, 256k context, and unmatched efficiency.
    Model
    coding
    5.61M
    3mo
    Z.ai

    glm4.7

    GLM-4.7 is a multilingual agentic coding partner with stronger reasoning, tool use, and UI skills.
    Model
    Tool Calling
    17.72M
    1mo
    OpenAI

    gpt-oss-120b

    Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
    Model
    text-to-text
    35.6M
    7mo
    OpenAI

    gpt-oss-20b

    Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
    Model
    text-to-text
    7.7M
    7mo
    Moonshotai

    kimi-k2-instruct

    State-of-the-art open mixture-of-experts model with strong reasoning, coding, and agentic capabilities
    Model
    coding
    19.99M
    7mo
    Moonshotai

    kimi-k2-instruct-0905

    Follow-on version of Kimi-K2-Instruct with longer context window and enhanced reasoning capabilities.
    Model
    long-context
    10M
    5mo
    Moonshotai

    kimi-k2-thinking

    Open reasoning model with 256K context window, native INT4 quantization and enhanced tool use.
    Model
    Conversational
    3.17M
    3mo
    NVIDIA

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

    Leading reasoning and agentic AI accuracy model for PC and edge.
    Model
    chat
    592K
    8mo
    NVIDIA

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

    High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
    Model
    chat
    1.09M
    7mo
    NVIDIA

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

    High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
    Model
    chat
    4.61M
    7mo
    Marin

    marin-8b-instruct

    State-of-the-art open model trained on open datasets, excelling in reasoning, math, and science.
    Model
    Reasoning
    474K
    9mo
    ByteDance

    seed-oss-36b-instruct

    ByteDance open-source LLM with long-context, reasoning, and agentic intelligence.
    Model
    thinking budget
    3.28M
    6mo
    Items per page
    of 3 pages