CLASSIC
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

NVIDIA Retrieval QA Mistral 7B Embedding v2Container
NVIDIA NIM for GPU accelerated NVIDIA Retrieval QA Mistral 7B Embedding v2 inference
+1
+1
Llama-3.1-8b-instruct PB October 2024 (PB 24h2)Container
NVIDIA NIM for GPU accelerated Llama 3.1 8B inference through OpenAI compatible APIs
+1
Meta/Llama3-70b-instructContainer
NVIDIA NIM for GPU accelerated Llama 3 70B inference through OpenAI compatible APIs
+1
+1
Qwen-2.5-7B-InstructContainer
NVIDIA NIM for GPU accelerated Qwen-2.5-7B-Instruct inference through OpenAI compatible APIs
+1

Getting Started

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
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.
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 Now
Documentation
We've got a whole host of documentation, covering the NGC UI and our powerful CLI. You can find out more here. Go to Documentation
AI Enterprise Documentation
Learn how to virtualize any application with NVIDIA virtual GPU technology. Go to Documentation
Enterprise Support
Get to access to knowledgebase articles and support cases. File a Ticket
Licensing Portal
Access the software & licensing portal for your products. Get Your Licenses
NGC Private Registry
Private Registries from NGC allow you to secure, manage, and deploy your own assets to accelerate your journey to AI. Learn More

Getting Started with NVIDIA AI Enterprise

Production Branch - October 2024 (PB 24h2)Collection - Deep Learning
Access the production branches of AI frameworks and SDKs. Supported for 9 months with monthly security patches.
+1
NeMo RetrieverCollection - Deep Learning
Nemo Retriever is a collection of NIMs reference architectures for RAG
+1
+1
NVIDIA AI Enterprise Infra 6Collection - Infrastructure
Access the latest infrastructure software and tools of the NVIDIA AI Enterprise 6 release, exclusively available with your NVIDIA AI Enterprise subscription. 
Long-Term Support Branch 2 (LTSB 2)Collection - Advanced
Access the Long-Term Support Branches (LTSB) of AI frameworks and SDKs. Supported for 36-months, with quarterly patches for high and critical software vulnerabilities.
+2

Getting Started with NVIDIA Omniverse Enterprise

Production Branch - December 2024 (PB 24h2)Collection - Advanced
Access the production branches of Omniverse frameworks and SDKs. Supported for 9 months with monthly security patches.
Kit SDKCollection - Advanced
Kit SDK is a toolkit for building native Omniverse applications and microservices.
+1
Omniverse Kit App StreamingCollection - Infrastructure
Omniverse Kit App Streaming
+1
USD Search APICollection - Deep Learning
AI-powered search for OpenUSD data, 3D models, images, and assets using text or image-based inputs.
+2
+1

Popular Collections

NeMo RetrieverDeep Learning
Nemo Retriever is a collection of NIMs reference architectures for RAG
+1
+1
Build an AI Chatbot with RAGMachine Learning
Use a reference application to build a fully functional retrieval-augmented generation (RAG)-based AI chatbot built with NVIDIA NIMTM microservices
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 text
Clara ParabricksHealthcare
Clara Parabricks is a collection of software tools and notebooks for next generation sequencing, including short- and long-read applications. These tools are designed to be scalable, generating highly accurate results in an accelerated compute environmen
Cosmos World Foundation ModelsDeep Learning
Cosmos World Foundation Models: A family of highly performant pre-trained world foundation models purpose-built for generating physics-aware videos and world states for physical AI development.

Popular Containers

Python Basic for AI Workbench
Python Basic - AI Workbench Default Container
python-cuda122
Python with CUDA 12.2 - AI Workbench Default Container (Beta)
DCGM
Manage and Monitor GPUs in Cluster Environments.
Validator for NVIDIA GPU Operator
Validates NVIDIA GPU Operator components

Popular Models

ChatGLM3-6B Chat Int4
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.
ESM-1nv
A NeMo Megatron BERT based model trained on protein sequences.
Llama2-13b Chat Int4
LlaMa 2 is a large language AI model capable of generating text and code in response to prompts.
Mistral-7B Chat Int4
The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets.

Popular Resources

Default Avatar Scene
The Default Avatar Scene is a pre-made 3D asset of an avatar scene compatible with the ACE Animation Pipeline.
Tokkio UI Web Assets
Static Web Assets for the Tokkio UI
tokkio_plugin_llm_rag
Resource for Tokkio LLM RAG plugin
Unreal Renderer Assets - Aki
Unreal renderer Aki asset for the Unreal Renderer microservice.

Popular Helm Charts

ucs-tokkio-app-base-1-stream-llm-rag-3d-ov
ucs-tokkio-app-base-1-stream-llm-rag-3d-ov
RAG Application: Multimodal Chatbot
This example showcases multi modal usecase in a RAG pipeline. It can understand any kind of images in PDF or .pptx (like graphs and plots) alongside text and tables.
RAG Application: Multiturn Chatbot
This example showcases a RAG workflow with multi-turn conversation capabilities.
RAG Application: Structured Data Chatbot
Sample RAG application which can handle question-answering from tabular data stored in CSV format.