NGC Catalog
Welcome Guest
All You Need to Build AI. All in One Place.Welcome to the NGC Catalog - GPU Accelerated AI models and SDKs that help you infuse AI into your applications at speed of light
NVIDIA NIM
MolMIMContainer
MolMIM is a transformer-based model developed by NVIDIA for controlled small molecule generation.+1
+2
Meta/Llama3-8b-instructContainer
NVIDIA NIM for GPU accelerated Llama 3 8B inference through OpenAI compatible APIs+1
+2
NVIDIA Retrieval QA E5 Embedding v5Container
NVIDIA NIM for GPU accelerated NVIDIA Retrieval QA E5 Embedding v5 inference+1
+1
TTS FastPitch HifiGAN RivaContainer
RIVA TTS NIM provide easy access to state-of-the-art text to speech models, capable of synthesizing English speech from text+1
+2
Getting Started
DeepStream - CV DeploymentCollection - Intelligent Video Analytics
DeepStream SDK delivers a complete streaming analytics toolkit for AI based video and image understanding and multi-sensor processing. The DeepStream SDK brings deep neural networks and other complex processing tasks into a stream processing pipeline.
Language ModellingCollection - Natural Language Processing
A collection of easy to use, highly optimized Deep Learning Models for Language Modelling. Deep Learning Examples provides Data Scientist and Software Engineers with recipes to Train, fine-tune, and deploy State-of-the-Art Models
NeMo - Automatic Speech RecognitionCollection - Automatic Speech Recognition
This collection contains NeMo models for Automatic Speech Recognition (ASR): Speech to Text, Speech Classification, Speaker Diarization, Speaker Verification, Speaker Recognition, Command Recognition, Voice Activity Detection
LLMs optimized for RTX PCsCollection - Windows Rtx Accelerated Models
A collection of TensorRT-LLM accelerated Windows RTX PC LLM models.Command Line Interface
Want to get more from NGC? Everything you see here can be used and managed via our powerful CLI tools. Download NowDocumentation
We've got a whole host of documentation, covering the NGC UI and our powerful CLI. You can find out more here. Go to DocumentationAI Enterprise Documentation
Learn how to virtualize any application with NVIDIA virtual GPU technology. Go to DocumentationEnterprise Support
Get to access to knowledgebase articles and support cases. File a TicketLicensing Portal
Access the software & licensing portal for your products. Get Your LicensesNGC Private Registry
Private Registries from NGC allow you to secure, manage, and deploy your own assets to accelerate your journey to AI. Learn MoreGetting Started with NVIDIA AI Enterprise
cuOptCollection - High Performance Computing
NVIDIA cuOpt is a world record GPU-accelerated optimization AI microservice that empowers instant dynamic decision-making to solve routing problems with the best-known accuracy at scale.Meta/Llama3-8b-instructContainer
NVIDIA NIM for GPU accelerated Llama 3 8B inference through OpenAI compatible APIs+1
+2
NVIDIA AI Enterprise Infra 5Collection - Infrastructure
Access Infrastructure and workload management software, exclusively available with your NVIDIA AI Enterprise subscription.
Production Branch - May 2024 (PB 24h1)Collection - Deep Learning
Access the production-ready branches of AI frameworks and SDKs. Supported for 9 months with monthly security patches.Popular Collections
HPC CollectionHigh Performance Computing
This collection provides access to the top HPC applications for Molecular Dynamics, Quantum Chemistry, and Scientific visualization.Production Branch - October 2023 (PB 23h2)Deep Learning
Access the production-ready branches of AI frameworks and SDKs. Supported for 9 months with monthly security patches.
Code LlamaAdvanced
Code Llama is an LLM capable of generating code, and natural language about code, from both code and natural language prompts.Llama 2Advanced
Llama 2 is a large language AI model capable of generating text and code in response to prompts.
Automatic Speech RecognitionAutomatic Speech Recognition
A collection of easy to use, highly optimized Deep Learning Models for Recommender Systems. Deep Learning Examples provides Data Scientist and Software Engineers with recipes to Train, fine-tune, and deploy State-of-the-Art Models
NVIDIA HoloscanHealthcare
The AI sensor processing platform
Clara DiscoveryHealthcare
Clara Discovery is a collection of frameworks, applications, and AI models enabling GPU-accelerated computational drug discovery
Clara NLPHealthcare
Clara NLP is a collection of SOTA biomedical pre-trained language models as well as highly optimized pipelines for training NLP models on biomedical and clinical textPopular Containers
Manage and Monitor GPUs in Cluster Environments.
Validates NVIDIA GPU Operator components
Manages NVIDIA Driver upgrades in Kubernetes cluster.
Manage MIG partitions in Kubernetes with a simple label change to a node.
Popular Models
ChatGLM3-6B is the latest open-source model in the ChatGLM series. ChatGLM3-6B introduces the following features (1) More Powerful Base Model (2) More Comprehensive Function Support (3) More Comprehensive Open-source Series.
EquiDock is an SE(3)-equivariant model that can predict protein-protein complex formation from two invidual proteins.
A NeMo Megatron BERT based model trained on protein sequences.
A 3 Billion parameter BERT based model that has model weights converted from Huggingface into NeMo Framework.
Popular Resources
Holoscan Sample App data for Endoscopy out of body detection
Video of cars for evaluating detection algorithms for Holoscan SDK.
Holoscan Sample App Data for AI Colonoscopy Segmentation of Polyps
Holoscan Sample App Data for AI-based Endoscopy Tool Tracking
Popular Helm Charts
The NVIDIA K8s Developer LLM Operator is an open source and easy to deploy Kubernetes Operator to self-host Generative AI workflows.
A Helm chart for deploying Nvidia System Management software on DGX Nodes
This Helm chart deploys the Digital Fingerprinting AI Workflow.
Enables your containerized applications to be profiled by NVIDIA DevTools applications (currently, only using NVIDIA Nsight Systems).