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

RUN ANYWHERE

deepseek-ai

deepseek-r1

advanced reasoningchat

State-of-the-art, high-efficiency LLM excelling in reasoning, math, and coding.

PREVIEW

nvidia

cosmos-1.0-diffusion-7b

physical aiimage-to-world

Generates physics-aware video world states from text and image prompts for physical AI development.

PREVIEW

nvidia

cosmos-1.0-autoregressive-5b

physical aipolicy evaluation

Generates future frames of a physics-aware world state based on simply an image or short video prompt for physical AI development.

RUN ANYWHERE

meta

llama-3.3-70b-instruct

instruction followingmath

Advanced LLM for reasoning, math, general knowledge, and function calling

RUN ANYWHERE

nvidia

llama-3.1-nemotron-70b-instruct

chatlanguage generation

Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA in order to improve the helpfulness of LLM generated responses.

RUN ANYWHERE

meta

llama-3.1-405b-instruct

synthetic data generationchat

Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks.

RUN ANYWHERE

meta

llama-3.2-90b-vision-instruct

image captioningimage-text retrieval

Cutting-edge vision-Language model exceling in high-quality reasoning from images.

PREVIEW

meta

llama-3.2-3b-instruct

chatlanguage generation

Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation.

PREVIEW

nvidia

nemotron-4-340b-reward

reward modelsynthetic data generation

Grades responses on five attributes helpfulness, correctness, coherence, complexity and verbosity.

RUN ANYWHERE

meta

llama-3.1-8b-instruct

chatlanguage generation

Advanced state-of-the-art model with language understanding, superior reasoning, and text generation.

RUN ANYWHERE

nv-mistralai

mistral-nemo-12b-instruct

chatcode generation

Most advanced language model for reasoning, code, multilingual tasks; runs on a single GPU.

RUN ANYWHERE

mistralai

mixtral-8x22b-instruct-v0.1

advanced reasoningchat

An MOE LLM that follows instructions, completes requests, and generates creative text.

PREVIEW

stabilityai

sdxl-turbo

image generationtext-to-image

A fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation

PREVIEW

nvidia

nemotron-4-340b-instruct

chatsynthetic data generation

Creates diverse synthetic data that mimics the characteristics of real-world data.

RUN ANYWHERE

google

gemma-2-9b-it

chatlanguage generation

Cutting-edge text generation model text understanding, transformation, and code generation.

PREVIEW

microsoft

phi-3-vision-128k-instruct

language generationvision assistant

Cutting-edge open multimodal model exceling in high-quality reasoning from images.

Blueprints to build and deploy Agentic AI applications, digital twins, etc.

PDF to Podcast

conversational aimulti-modalpdf-to-podcasttext-to-speech

Transform PDFs into AI podcasts for engaging on-the-go audio content.

Multimodal PDF Data Extraction

augmented generationgenerative aiingestionmultimodal

Ingest and extract highly accurate insights contained in text, graphs, charts, and tables within massive volumes of PDF documents.

Vulnerability Analysis for Container Security

nvidia aicybersecuritygenerative aillama-3_1-70b-instruct

Rapidly identify and mitigate container security vulnerabilities with generative AI.

Build an AI Virtual Assistant

customer serviceretrieval-augmented generationnvidia aicontact center

Create intelligent virtual assistants for customer service across every industry

Build a Video Search and Summarization Agent

nvidia aichatgenerative aivideo-to-text

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

Build a Digital Human

audio-to-facechatdigital humansspeech-to-text

Create intelligent, interactive avatars for customer service across industries

Reference blueprints co-developed with leading agentic AI platform providers.

crewai

Code Documentation for Software Development

ai agentsblueprint

Document your github repositories with AI Agents using CrewAI and Llama3.3 70B NIM.

langchain

Structured Report Generation

ai agentsblueprint

Generate detailed, structured reports on any topic using LangGraph and Llama3.3 70B NIM

llamaindex

Document Research Assistant for Blog Creation

ai agentsblog creation

Automate research, and generate blogs with AI Agents using LlamaIndex and Llama3.3-70B NIM LLM.

pipecat

Voice Agent Framework for Conversational AI

ai agentsblueprint

Automate voice AI agents with NVIDIA NIM microservices and Pipecat.

wandb

Traceability for Agentic AI

ai agentsblueprint

Trace and evaluate AI Agents with Weights & Biases.