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

  • Free Endpoint
    9
  • Partner Endpoint
    14
  • Download Available
    16
  • Code Generation
    4
  • Text Translation
    1
  • Retrieval Augmented Generation
    0
  • Drug Discovery
    0
  • Image-to-Text
    0
  • Together AI
    10
  • Deep Infra
    8
  • GMI Cloud
    7
  • CoreWeave
    3
  • Digital Ocean
    3
  • NVIDIA
    5
  • DeepSeek AI
    4
  • Microsoft
    3
  • Qwen
    3
  • Mistral AI
    2
  • Enterprise
    0
  • NVIDIA BioNemo
    0
    • 25 models
    OpenAI
    Downloadable

    gpt-oss-20b

    Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
    reasoning
    7.78M
    8mo
    OpenAI
    Downloadable

    gpt-oss-120b

    Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
    reasoning
    42.11M
    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.
    chat
    2.39M
    8mo
    Sarvamai
    Downloadable

    sarvam-m

    Multilingual, hybrid-reasoning model optimized for Indian language tasks, programming, mathematical reasoning capabilities.
    coding
    153K
    8mo
    Microsoft
    Deprecation in 6dFree Endpoint

    phi-4-mini-flash-reasoning

    Lightweight reasoning model for applications in latency bound, memory/compute constrained environments
    chat
    120K
    8mo
    Mistral AI
    Free Endpoint

    magistral-small-2506

    High performance reasoning model optimized for efficiency and edge deployment
    coding
    1.14M
    9mo
    NVIDIA
    Deprecation in 6dDownloadable

    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
    chat
    111K
    9mo
    Marin
    Free Endpoint

    marin-8b-instruct

    State-of-the-art open model trained on open datasets, excelling in reasoning, math, and science.
    chat
    113K
    10mo
    NVIDIA
    Downloadable

    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.
    chat
    4.72M
    9mo
    Qwen
    Deprecation in 6dFree Endpoint

    qwq-32b

    Powerful reasoning model capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems.
    coding
    1.22M
    9mo
    NVIDIA
    Deprecation in 6dDownloadable

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

    High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
    chat
    1.19M
    8mo
    NVIDIA
    Downloadable

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

    Leading reasoning and agentic AI accuracy model for PC and edge.
    chat
    485K
    9mo
    DeepSeek AI
    Downloadable

    deepseek-r1-distill-llama-8b

    Distilled version of Llama 3.1 8B using reasoning data generated by DeepSeek R1 for enhanced performance.
    Distillation
    1.36M
    9mo
    DeepSeek AI
    Downloadable

    deepseek-r1-distill-qwen-32b

    Distilled version of Qwen 2.5 32B using reasoning data generated by DeepSeek R1 for enhanced performance.
    coding
    7.76K1.64M
    10mo
    DeepSeek AI
    Downloadable

    deepseek-r1-distill-qwen-14b

    Distilled version of Qwen 2.5 14B using reasoning data generated by DeepSeek R1 for enhanced performance.
    coding
    2.29K1.24M
    10mo
    DeepSeek AI
    Downloadable

    deepseek-r1-distill-qwen-7b

    Distilled version of Qwen 2.5 7B using reasoning data generated by DeepSeek R1 for enhanced performance.
    coding
    2.75K1.28M
    10mo
    Mistral AI
    Downloadable

    mistral-small-24b-instruct

    Latency-optimized language model excelling in code, math, general knowledge, and instruction-following.
    chat
    203K
    9mo
    Tiiuae
    Free Endpoint

    falcon3-7b-instruct

    Instruction tuned LLM achieving SoTA performance on reasoning, math and general knowledge capabilities
    chat
    421K
    10mo
    Qwen
    Downloadable

    qwen2.5-7b-instruct

    Chinese and English LLM targeting for language, coding, mathematics, reasoning, etc.
    Chinese Language Generation
    8.03M
    10mo
    Meta
    Downloadable

    llama-3.3-70b-instruct

    Advanced LLM for reasoning, math, general knowledge, and function calling
    Instruction following
    13.28M
    10mo
    Qwen
    Free Endpoint

    qwen2-7b-instruct

    Chinese and English LLM targeting for language, coding, mathematics, reasoning, etc.
    Chinese Language Generation
    205K
    10mo
    Baichuan AI
    Free Endpoint

    baichuan2-13b-chat

    Support Chinese and English chat, coding, math, instruction following, solving quizzes
    Chinese Language Generation
    145K
    10mo
    Upstage
    Free Endpoint

    solar-10.7b-instruct

    Excels in NLP tasks, particularly in instruction-following, reasoning, and mathematics.
    Non-Commercial Use Only
    93.54K
    12mo
    Microsoft
    Downloadable

    phi-3-mini-4k-instruct

    Lightweight, state-of-the-art open LLM with strong math and logical reasoning skills.
    chat
    95.57K
    10mo
    Items per page
    of 2 pages