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

Copyright © 2026 NVIDIA Corporation

16 results for

Filters (1)

  • API Endpoint
    12
  • Download Available
    5
  • Launchable
    0
  • Enterprise
    0
  • Image-to-Text
    13
  • Code Generation
    0
  • Drug Discovery
    0
  • Retrieval Augmented Generation
    0
  • Object Detection
    0
  • Meta
    4
  • Mistral AI
    3
  • NVIDIA
    2
  • Microsoft
    2
  • Google
    2
  • NVIDIA AI
    0
  • NVIDIA Omniverse
    0
  • NVIDIA BioNemo
    0
  • NVIDIA Isaac GR00T
    0
  • Image-to-Text
    • University at Buffalo
    API Endpoint

    cached

    Context-aware chart extraction that can detect 18 classes for chart basic elements, excluding plot elements.
    Model
    nemo retriever
    737
    1y
    NVIDIA
    API Endpoint

    cosmos-nemotron-34b

    Multi-modal vision-language model that understands text/img/video and creates informative responses
    Model
    VLM
    6
    1y
    Google
    API Endpoint

    gemma-3-27b-it

    Cutting-edge open multimodal model exceling in high-quality reasoning from images.
    Model
    chat
    5.79M
    9mo
    Moonshotai
    Downloadable

    kimi-k2.5

    1T multimodal MoE for high‑capacity video and image understanding with efficient inference.
    Model
    chat
    22.84M
    1mo
    Meta
    Downloadable

    llama-3.2-11b-vision-instruct

    Cutting-edge vision-language model exceling in high-quality reasoning from images.
    Model
    chat
    844K
    9mo
    Meta
    Downloadable

    llama-3.2-90b-vision-instruct

    Cutting-edge vision-Language model exceling in high-quality reasoning from images.
    Model
    chat
    624K
    9mo
    Meta
    API Endpoint

    llama-4-maverick-17b-128e-instruct

    A general purpose multimodal, multilingual 128 MoE model with 17B parameters.
    Model
    chat
    3.25M
    7mo
    Meta
    DownloadableAPI Endpoint

    llama-4-scout-17b-16e-instruct

    A multimodal, multilingual 16 MoE model with 17B parameters.
    Model
    chat
    156K
    7mo
    Mistral AI
    API Endpoint

    ministral-14b-instruct-2512

    A general purpose VLM ideal for chat and instruction based use cases
    Model
    chat
    4.67M
    3mo
    Mistral AI
    API 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.
    Model
    chat
    6.69M
    3mo
    Mistral AI
    API Endpoint

    mistral-medium-3-instruct

    Powerful, multimodal language model designed for enterprise applications, including software development, data analysis, and reasoning.
    Model
    chat
    5.28M
    8mo
    NVIDIA
    Downloadable

    nemotron-nano-12b-v2-vl

    Nemotron Nano 12B v2 VL enables multi-image and video understanding, along with visual Q&A and summarization capabilities.
    Model
    chat
    1.4M
    4mo
    Google
    API Endpoint

    paligemma

    Vision language model adept at comprehending text and visual inputs to produce informative responses
    Model
    image
    335K
    1y
    Microsoft
    API Endpoint

    phi-3.5-vision-instruct

    Cutting-edge open multimodal model exceling in high-quality reasoning from images.
    Model
    Vision Assistant
    592K
    1y
    Microsoft
    API Endpoint

    phi-4-multimodal-instruct

    Cutting-edge open multimodal model exceling in high-quality reasoning from image and audio inputs.
    Model
    Speech Recognition
    532K
    9mo
    Qwen
    API Endpoint

    qwen3.5-122b-a10b

    122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
    Model
    chat
    1.49M
    1w
    Items per page
    of 1 pages