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 (1)

  • Free Endpoint
    9
  • Partner Endpoint
    10
  • Download Available
    8
  • Image-to-Text
    13
  • Code Generation
    0
  • Retrieval Augmented Generation
    0
  • Drug Discovery
    0
  • Object Detection
    0
  • Deep Infra
    7
  • Bitdeer AI
    6
  • Together AI
    4
  • GMI Cloud
    3
  • CoreWeave
    1
  • Meta
    4
  • Mistral AI
    4
  • Microsoft
    2
  • Google
    2
  • NVIDIA
    1
  • Enterprise
    0
  • NVIDIA BioNemo
    0
  • Image-to-Text
    • 16 models
    Mistral AI
    Downloadable

    mistral-small-4-119b-2603

    Hybrid MoE model unifying instruct, reasoning, and coding with multimodal input and 256k context
    code generation
    7.15M
    1mo
    Qwen
    Downloadable

    qwen3.5-122b-a10b

    122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
    tool calling
    8.34M
    1mo
    Moonshotai
    Downloadable

    kimi-k2.5

    1T multimodal MoE for high‑capacity video and image understanding with efficient inference.
    Multimodal
    51.97M
    2mo
    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
    5.4M
    4mo
    Mistral AI
    Downloadable

    ministral-14b-instruct-2512

    A general purpose VLM ideal for chat and instruction based use cases
    language generation
    1.47M
    4mo
    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.
    language generation
    4.58M
    5mo
    Mistral AI
    Free Endpoint

    mistral-medium-3-instruct

    Powerful, multimodal language model designed for enterprise applications, including software development, data analysis, and reasoning.
    language generation
    1.5M
    9mo
    Meta
    Free Endpoint

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

    A general purpose multimodal, multilingual 128 MoE model with 17B parameters.
    language generation
    8.25M
    9mo
    Meta
    DownloadableFree Endpoint

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

    A multimodal, multilingual 16 MoE model with 17B parameters.
    language generation
    20.14K
    9mo
    Google
    Free Endpoint

    gemma-3-27b-it

    Cutting-edge open multimodal model exceling in high-quality reasoning from images.
    Vision Assistant
    5.92M
    10mo
    Microsoft
    Free Endpoint

    phi-4-multimodal-instruct

    Cutting-edge open multimodal model exceling in high-quality reasoning from image and audio inputs.
    Speech Recognition
    324K
    10mo
    University at Buffalo
    Free Endpoint

    cached

    Context-aware chart extraction that can detect 18 classes for chart basic elements, excluding plot elements.
    nemo retriever
    156
    1y
    Meta
    Downloadable

    llama-3.2-11b-vision-instruct

    Cutting-edge vision-language model exceling in high-quality reasoning from images.
    Image-Text Retrieval
    1.01M
    10mo
    Meta
    Downloadable

    llama-3.2-90b-vision-instruct

    Cutting-edge vision-Language model exceling in high-quality reasoning from images.
    Image-Text Retrieval
    1.17M
    10mo
    Microsoft
    DeprecatedFree Endpoint

    phi-3.5-vision-instruct

    Cutting-edge open multimodal model exceling in high-quality reasoning from images.
    Vision Assistant
    1.22M
    1y
    Google
    Free Endpoint

    paligemma

    Vision language model adept at comprehending text and visual inputs to produce informative responses
    image
    44.48K
    1y
    Items per page
    of 1 pages