Deploy Models Now with NVIDIA NIM
Optimized inference for the world’s leading models
Most Popular Models
View AllThe leading open models built by the community, optimized and accelerated by NVIDIA's enterprise-ready inference runtime.
metallama-4-maverick-17b-128e-instruct
A general purpose multimodal, multilingual 128 MoE model with 17B parameters.
metallama-4-scout-17b-16e-instruct
A multimodal, multilingual 16 MoE model with 17B parameters.
nvidiallama-3.1-nemotron-ultra-253b-v1
Superior inference efficiency with highest accuracy for scientific and complex math reasoning, coding, tool calling, and instruction following.
nvidiallama-3.3-nemotron-super-49b-v1
High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
deepseek-aideepseek-r1
State-of-the-art, high-efficiency LLM excelling in reasoning, math, and coding.
nvidiallama-3.1-nemotron-nano-8b-v1
Leading reasoning and agentic AI accuracy model for PC and edge.
googlegemma-3-27b-it
Cutting-edge open multimodal model exceling in high-quality reasoning from images.
microsoftphi-4-multimodal-instruct
Cutting-edge open multimodal model exceling in high-quality reasoning from image and audio inputs.
nvidiacosmos-predict1-7b
Generates physics-aware video world states from text and image prompts for physical AI development.
Create AI Agents
View AllBlueprints to build and deploy Agentic AI applications, digital twins, etc.
nvidiaBuild an AI Agent for Research and Reporting
Create AI agents that reason, plan, reflect and refine to produce high-quality reports based on source materials of your choice.
nvidiaLLM Router
Route LLM requests to the best model for the task at hand.
nvidiaPDF to Podcast
Transform PDFs into AI podcasts for engaging on-the-go audio content.
nvidiaBuild an Enterprise RAG pipeline
Connect AI applications to multimodal enterprise data with a scalable retrieval augmented generation (RAG) pipeline built on highly performant, industry-leading NIM microservices, for faster PDF data extraction and more accurate information retrieval.
crewaiCode Documentation for Software Development
Document your github repositories with AI Agents using CrewAI and Llama3.3 70B NIM.
langchainStructured Report Generation
Generate detailed, structured reports on any topic using LangGraph and Llama3.3 70B NIM
llamaindexDocument Research Assistant for Blog Creation
Automate research, and generate blogs with AI Agents using LlamaIndex and Llama3.3-70B NIM LLM.
pipecatVoice Agent Framework for Conversational AI
Automate voice AI agents with NVIDIA NIM microservices and Pipecat.
wandbTraceability for Agentic AI
Trace and evaluate AI Agents with Weights & Biases.
Discover
AI Models for RTX AI PCs and Workstations
View AllSpanning language, speech, animation, content generation, and vision capabilities, run NVIDIA NIM microservices on your RTX AI PC.
deepseek-aideepseek-r1-distill-llama-8b
Distilled version of Llama 3.1 8B using reasoning data generated by DeepSeek R1 for enhanced performance.
black-forest-labsFLUX.1-dev
FLUX.1 is a state-of-the-art suite of image generation models
nv-mistralaimistral-nemo-12b-instruct
Most advanced language model for reasoning, code, multilingual tasks; runs on a single GPU.
metallama-3.1-8b-instruct
Advanced state-of-the-art model with language understanding, superior reasoning, and text generation.
nvidiaparakeet-ctc-0.6b-asr
State-of-the-art accuracy and speed for English transcriptions.
nvidiastudiovoice
Enhance speech by correcting common audio degradations to create studio quality speech output.
nvidiallama-3.2-nv-embedqa-1b-v2
Multilingual and cross-lingual text question-answering retrieval with long context support and optimized data storage efficiency.
nvidianv-yolox-page-elements-v1
Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
Develop Physical AI
View AllPre-trained foundation models and blueprints for digital twins, synthetic data generation, and robotic simulation to accelerate Physical AI development.
nvidiaTest Multi-Robot Fleets for Industrial Automation
Simulate, test, and optimize physical AI and robotic fleets at scale in industrial digital twins before real-world deployment.
nvidiaSynthetic Manipulation Motion Generation for Robotics
Generate exponentially large amounts of synthetic motion trajectories for robot manipulation from just a few human demonstrations.
nvidiacosmos-predict1-7b
Generates physics-aware video world states from text and image prompts for physical AI development.
nvidiacosmos-predict1-5b
Generates future frames of a physics-aware world state based on simply an image or short video prompt for physical AI development.
nvidiaBuild a Digital Twin for Interactive Fluid Simulation
This NVIDIA Omniverse™ Blueprint demonstrates how commercial software vendors can create interactive digital twins.
Accelerate Your Simulation Workflows
View AllBlueprints to help you expedite simulation and development with NVIDIA Omniverse.
nvidiaAI Weather Analytics with Earth-2
Develop AI powered weather analysis and forecasting application visualizing multi-layered geospatial data.
nvidiaBuild a Digital Twin for Interactive Fluid Simulation
This NVIDIA Omniverse™ Blueprint demonstrates how commercial software vendors can create interactive digital twins.
nvidiaBuild a Digital Human
Create intelligent, interactive avatars for customer service across industries
nvidia3D Conditioning for Precise Visual Generative AI
Enhance and modify high-quality compositions using real-time rendering and generative AI output without affecting a hero product asset.
nvidiaSynthetic Manipulation Motion Generation for Robotics
Generate exponentially large amounts of synthetic motion trajectories for robot manipulation from just a few human demonstrations.
nvidiaTest Multi-Robot Fleets for Industrial Automation
Simulate, test, and optimize physical AI and robotic fleets at scale in industrial digital twins before real-world deployment.
Accelerated Computing for Digital Biology
View AllAI-driven drug discovery and accelerated genomics workflows.
nvidiaGenomics Analysis
Easily run essential genomics workflows to save time leveraging Parabricks
nvidiaSingle Cell Analysis
Investigate, understand, and interpret single cell data in minutes, not days by leveraging RAPIDS-singlecell, powered by NVIDIA RAPIDS
nvidiaBuild A Generative Protein Binder Design Pipeline
This blueprint shows how generative AI and accelerated NIM microservices can design protein binders smarter and faster.
nvidiaBuild A Generative Virtual Screening Pipeline
This blueprint shows how generative AI and accelerated NIM microservices can design optimized small molecules smarter and faster.