SearchSearch thousands of GPU-optimized Containers, pretrained Models, SDKs, and Helm charts—ready to accelerate AI, digital twins, and HPC from cloud to edge.
NVIDIA AI Enterprise
NVIDIA AI Enterprise
  • NVIDIA NIM
    NVIDIA NIM
  • NIM Container GPUs
    NIM Container GPUs
  • Use Case
    Use Case
    7
    5
    1
    1
    1
  • NVIDIA Platform
    NVIDIA Platform
    3
    2
    1
    1
    1
  • Industry
    Industry
    10
    5
    4
    1
  • Solution
    Solution
    11
    4
    3
    1
  • Publisher
    Publisher
    18
    2
  • Policy
    Policy
  • Displaying 20 results
    Sample models, segmentations and videos from ORSI Academy to be used with Holoscan SDK
    Resource
    Holoscan Sample App Data for AI-based Endoscopy Depth Estimation
    Resource
    NVIDIA BioNeMo
    NVIDIA BioNeMo
    GenMol
    GenMol Model V2 Weights
    Resource
    NVIDIA BioNeMo
    NVIDIA BioNeMo
    GenMol
    GenMol Model V2 Weights
    Resource
    This collection contains the large version (114M) of the English speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 1024 and emits text with punctuation and capitalization.
    Model
    This collection contains the large version (114M) of the German speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 1024 and emits text with punctuation and capitalization.
      Model
      This collection contains the large version (114M) of the Spanish speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 1024 and emits text with punctuation and capitalization.
      Model
      This collection contains the large version (114M) of the Ukrainian speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 1024 and emits text with punctuation and capitalization.
      Model
      This collection contains the large version (114M) of the Polish speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 1024 and emits text with punctuation and capitalization.
      Model
      Base Hindi 3-gram LM
        Model
        NVIDIA
        NVIDIA
        avgflow
        AvgFlow Model Weights
        Resource
        RNAPro Model Weights
        Resource
        This collection contains the large version (114M) of the Dutch speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 1024 and emits text with punctuation and capitalization.
        Model
        Nemotron-Mini-4B-Instruct pruned and distilled from the Nemotron-4 15B model designed for on-device inference and conversational roleplay.
        Resource
        NVIDIA
        NVIDIA
        avgflow
        AvgFlow Model Weights
        Resource
        This collection contains the large version (114M) of the Belarusian speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 1024 and emits text with punctuation and capitalization.
          Model
          Holoscan sample app data for colonoscopy tracking application.
          Resource
          This collections contains the large version (114M) of the Croatian speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 256 and emits text with punctuation and capitalization.
          Model
          NVIDIA
          NVIDIA
          avgflow
          AvgFlow Model Weights
          Resource
          NVIDIA
          NVIDIA
          avgflow
          AvgFlow Model Weights
          Resource