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 (1)

  • Free Endpoint
    4
  • Partner Endpoint
    2
  • Download Available
    4
  • Image-to-Text
    3
  • Drug Discovery
    0
  • Retrieval Augmented Generation
    0
  • Speech-to-Text
    0
  • Image Generation
    0
  • OpenRouter
    2
  • Deepinfra
    2
  • Together AI
    2
  • GMI Cloud
    1
  • Bitdeer
    1
  • Mistral AI
    2
  • Meta
    1
  • Moonshotai
    1
  • Thinkingmachines
    1
  • NVIDIA
    0
  • H100 80GB HBM3
    0
  • A100 SXM4 80GB
    0
  • L40S
    0
  • A10G
    0
  • B200
    0
  • Multimodal
    • 5 models
    Thinkingmachines
    DownloadableFree Endpoint

    inkling

    Inkling is a multimodal (text + image) reasoning model from Thinking Machines — a Mamba-hybrid, 256-expert Mixture-of-Experts architecture with tool use and switchable reasoning.
    text-to-text
    Today
    Items per page
    of 1 pages
    Moonshotai
    DownloadableFree Endpoint

    kimi-k2.6

    1T multimodal MoE for long-horizon coding, agentic tool use, and image/video understanding.
    Multimodal
    16M
    2mo
    Mistral AI
    Downloadable

    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
    2M
    7mo
    Mistral AI
    DownloadableFree Endpoint

    ministral-14b-instruct-2512

    A general purpose VLM ideal for chat and instruction based use cases
    language generation
    4M
    7mo
    Meta
    Free Endpoint

    llama-guard-4-12b

    Multi-modal model to classify safety for input prompts as well output responses.
    LLM Multimodal Safety
    357K
    1y