The leading open models built by the community, optimized and accelerated by NVIDIA's enterprise-ready inference runtime.

nvidiallama-3.1-nemotron-safety-guard-8b-v3

Leading multilingual content safety model for enhancing the safety and moderation capabilities of LLMs

content moderationllm safetymultilingual content safetymultilingual guard modelnemoguard

Run Anywhere

nvidianemotron-nano-12b-v2-vl

Nemotron Nano 12B v2 VL enables multi-image and video understanding, along with visual Q&A and summarization capabilities.

language generationImage-to-Textvision assistantvisual question answering

Run Anywhere

openaigpt-oss-20b

Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math

mathchatreasoningtext-to-text

Run Anywhere

qwenqwen3-next-80b-a3b-thinking

80B parameter AI model with hybrid reasoning, MoE architecture, support for 119 languages.

ReasoningText-to-Text

Get started with workflows and code samples to build AI applications from the ground up.

cyborgCyborg Enterprise RAG

Securely extract, embed, and index multimodal data with encryption in-use for fast, accurate semantic search.

BlueprintNIMNeMo RetrieverRetrieval-Augmented GenerationLaunchable

h2oFlood Intelligence

H2O.ai Flood Intelligence provides real-time, scalable intelligence for AI-powered disaster management.

BlueprintPartnerRisk AnalysisLaunchableNVIDIA AI

nvidiaBuild an AI Agent for Enterprise Research

Build a custom enterprise research assistant powered by state-of-the-art models that process and synthesize multimodal data, enabling reasoning, planning, and refinement to generate comprehensive reports.

BlueprintLlama NemotronNIMNeMo RetrieverReasoningRetrieval-Augmented GenerationEnterpriseLaunchableNVIDIA AI

nvidiaBuild a Video Search and Summarization (VSS) Agent

Ingest massive volumes of live or archived videos and extract insights for summarization and interactive Q&A

BlueprintEnterpriseLaunchableNVIDIA AIchatgenerative AIvideo-to-textvision