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

Copyright © 2026 NVIDIA Corporation

4 results for

Filters (1)

  • API Endpoint
    4
  • Download Available
    1
  • Launchable
    0
  • Enterprise
    0
  • Image-to-Text
    4
  • Retrieval Augmented Generation
    0
  • Text-to-Embedding
    0
  • Image Generation
    0
  • Text-to-Image
    0
  • Meta
    2
  • Microsoft
    1
  • Google
    1
  • NVIDIA
    0
  • Mistral AI
    0
  • NVIDIA AI
    0
  • Vision Assistant
    • Meta

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

    A multimodal, multilingual 16 MoE model with 17B parameters.
    Model
    language generation
    263K
    7mo
    Google

    gemma-3-27b-it

    Cutting-edge open multimodal model exceling in high-quality reasoning from images.
    Model
    Vision Assistant
    5.33M
    9mo
    Meta

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

    A general purpose multimodal, multilingual 128 MoE model with 17B parameters.
    Model
    language generation
    2.75M
    7mo
    Microsoft

    phi-3.5-vision-instruct

    Cutting-edge open multimodal model exceling in high-quality reasoning from images.
    Model
    Vision Assistant
    478K
    1y
    Items per page
    of 1 pages