The leading open models built by the community, optimized and accelerated by NVIDIA's enterprise-ready inference runtime.
A general purpose multimodal, multilingual 128 MoE model with 17B parameters.
Superior inference efficiency with highest accuracy for scientific and complex math reasoning, coding, tool calling, and instruction following.
Powerful, multimodal language model designed for enterprise applications, including software development, data analysis, and reasoning.
State-of-the-art, high-efficiency LLM excelling in reasoning, math, and coding.
High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
A multimodal, multilingual 16 MoE model with 17B parameters.
Leading reasoning and agentic AI accuracy model for PC and edge.
Cutting-edge open multimodal model exceling in high-quality reasoning from images.
Cutting-edge open multimodal model exceling in high-quality reasoning from image and audio inputs.
Generates physics-aware video world states from text and image prompts for physical AI development.
Blueprints to build and deploy Agentic AI applications, digital twins, etc.
Create AI agents that reason, plan, reflect and refine to produce high-quality reports based on source materials of your choice.
Route LLM requests to the best model for the task at hand.
Transform PDFs into AI podcasts for engaging on-the-go audio content.
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.
Document your github repositories with AI Agents using CrewAI and Llama3.3 70B NIM.
Generate detailed, structured reports on any topic using LangGraph and Llama3.3 70B NIM
Automate research, and generate blogs with AI Agents using LlamaIndex and Llama3.3-70B NIM LLM.
Automate voice AI agents with NVIDIA NIM microservices and Pipecat.
Trace and evaluate AI Agents with Weights & Biases.
Spanning language, speech, animation, content generation, and vision capabilities, run NVIDIA NIM microservices on your RTX AI PC.
Distilled version of Llama 3.1 8B using reasoning data generated by DeepSeek R1 for enhanced performance.
FLUX.1 is a state-of-the-art suite of image generation models
Most advanced language model for reasoning, code, multilingual tasks; runs on a single GPU.
Advanced state-of-the-art model with language understanding, superior reasoning, and text generation.
State-of-the-art accuracy and speed for English transcriptions.
Enhance speech by correcting common audio degradations to create studio quality speech output.
Multilingual and cross-lingual text question-answering retrieval with long context support and optimized data storage efficiency.
Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
Pre-trained foundation models and blueprints for digital twins, synthetic data generation, and robotic simulation to accelerate Physical AI development.
Simulate, test, and optimize physical AI and robotic fleets at scale in industrial digital twins before real-world deployment.
Generate exponentially large amounts of synthetic motion trajectories for robot manipulation from just a few human demonstrations.
Generates physics-aware video world states from text and image prompts for physical AI development.
Generates future frames of a physics-aware world state based on simply an image or short video prompt for physical AI development.
This NVIDIA Omniverse™ Blueprint demonstrates how commercial software vendors can create interactive digital twins.
Blueprints to help you expedite simulation and development with NVIDIA Omniverse.
Develop AI powered weather analysis and forecasting application visualizing multi-layered geospatial data.
This NVIDIA Omniverse™ Blueprint demonstrates how commercial software vendors can create interactive digital twins.
Create intelligent, interactive avatars for customer service across industries
Enhance and modify high-quality compositions using real-time rendering and generative AI output without affecting a hero product asset.
Generate exponentially large amounts of synthetic motion trajectories for robot manipulation from just a few human demonstrations.
Simulate, test, and optimize physical AI and robotic fleets at scale in industrial digital twins before real-world deployment.
AI-driven drug discovery and accelerated genomics workflows.
Easily run essential genomics workflows to save time leveraging Parabricks
Investigate, understand, and interpret single cell data in minutes, not days by leveraging RAPIDS-singlecell, powered by NVIDIA RAPIDS
This blueprint shows how generative AI and accelerated NIM microservices can design protein binders smarter and faster.
This blueprint shows how generative AI and accelerated NIM microservices can design optimized small molecules smarter and faster.
