Skip to main content
NVIDIA
Explore
Models
Skills
Blueprints
GPUs
Docs
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
    22
  • Partner Endpoint
    10
  • Download Available
    30
  • Retrieval Augmented Generation
    6
  • Object Detection
    4
  • Image-to-Text
    3
  • Optical Character Recognition
    3
  • Text-to-Embedding
    2
  • Deepinfra
    7
  • OpenRouter
    4
  • Bitdeer
    4
  • Lightning AI
    3
  • Together AI
    2
  • NVIDIA
    35
  • Mistral AI
    4
  • Meta
    0
  • Google
    0
  • Qwen
    0
  • H100 80GB HBM3
    3
  • H200
    3
  • L40S
    3
  • A100 SXM4 80GB
    3
  • A10G
    3
    • 39 models
    NVIDIA
    Downloadable

    nemotron-ocr-v2

    Nemotron OCR v2 is a state-of-the-art multilingual text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images.
    Table Extraction
    338K
    18d
    Items per page
    of 2 pages
    NVIDIA
    DownloadableFree Endpoint

    nemotron-3-ultra-550b-a55b

    Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
    Agent
    8M
    1mo
    NVIDIA
    DownloadableFree Endpoint

    nemotron-3.5-content-safety

    Multilingual, multimodal model for detecting unsafe and toxic content.
    llm safety
    2M
    1mo
    Mistral AI
    DownloadableFree Endpoint

    mistral-medium-3.5-128b

    A high performing model for text generation, coding and agentic use cases
    coding
    4M
    2mo
    NVIDIA
    DownloadableFree Endpoint

    nemotron-3-nano-omni-30b-a3b-reasoning

    Nemotron 3 Nano Omni is an omni-modal reasoning model that understands images, video, speech, text.
    Image-to-Text
    8M
    2mo
    NVIDIA
    Deprecation in 3dFree Endpoint

    nemotron-3-content-safety

    Multilingual, multimodal model for detecting unsafe and toxic content.
    llm safety
    295K
    2mo
    NVIDIA
    Downloadable

    llama-nemotron-rerank-vl-1b-v2

    GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.
    nemo retriever
    84K
    3mo
    Mistral AI
    DownloadableFree Endpoint

    mistral-small-4-119b-2603

    Hybrid MoE model unifying instruct, reasoning, and coding with multimodal input and 256k context
    code generation
    13M
    3mo
    NVIDIA
    Free Endpoint

    nemotron-voicechat

    Nemotron 3 Voicechat
    English
    2K
    3mo
    NVIDIA
    Downloadable

    nemotron-asr-streaming

    Real-time speech recognition for English
    Automatic Speech Recognition
    6K
    4mo
    NVIDIA
    Downloadable

    nemotron-ocr-v1

    Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.
    Table Extraction
    341K
    4mo
    NVIDIA
    DownloadableFree Endpoint

    nemotron-3-super-120b-a12b

    Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
    MoE
    60M
    4mo
    NVIDIA
    Downloadable

    llama-nemotron-rerank-1b-v2

    GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.
    nemo retriever
    501K
    4mo
    NVIDIA
    Downloadable

    nemotron-table-structure-v1

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Object Detection
    157K
    4mo
    NVIDIA
    Downloadable

    nemotron-page-elements-v3

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Object Detection
    433K
    4mo
    NVIDIA
    Downloadable

    nemotron-graphic-elements-v1

    Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
    Object Detection
    40K
    4mo
    NVIDIA
    Downloadable

    llama-nemotron-embed-1b-v2

    Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.
    Text-to-Embedding
    4M
    4mo
    NVIDIA
    Downloadable

    llama-nemotron-embed-vl-1b-v2

    Multimodal question-answer retrieval representing user queries as text and documents as images.
    nemo retriever
    8M
    5mo
    NVIDIA
    Deprecation in 3dFree Endpoint

    nemotron-content-safety-reasoning-4b

    A context‑aware safety model that applies reasoning to enforce domain‑specific policies.
    NeMo Guardrails
    504K
    5mo
    NVIDIA
    DownloadableFree Endpoint

    nemotron-3-nano-30b-a3b

    Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more
    MoE
    12M
    6mo
    Mistral AI
    Free Endpoint

    mistral-large-3-675b-instruct-2512

    A state-of-the-art general purpose MoE VLM ideal for chat, agentic and instruction based use cases.
    language generation
    3M
    7mo
    NVIDIA
    Downloadable

    nemotron-parse

    Cutting-edge vision-language model exceling in retrieving text and metadata from images.
    text and table extraction
    218K
    8mo
    NVIDIA
    DownloadableFree Endpoint

    nemotron-nano-12b-v2-vl

    Nemotron Nano 12B v2 VL enables multi-image and video understanding, along with visual Q&A and summarization capabilities.
    language generation
    2M
    8mo
    NVIDIA
    Free Endpoint

    llama-3.1-nemotron-safety-guard-8b-v3

    Leading multilingual content safety model for enhancing the safety and moderation capabilities of LLMs
    content moderation
    336K
    8mo