NVIDIA
Explore Models Blueprints GPUs Docs

Deploy Models Now with NVIDIA NIM

Optimized inference for the world’s leading models
Free serverless APIs for developmentAccelerated by DGX Cloud
Self-Host on your GPU infrastructure
Continuous vulnerability fixes
DiscoverModelsBlueprintsGPUsDocsForums
models
ReasoningVisionVisual DesignRetrievalSpeechBiologySimulationClimate & WeatherSafety & ModerationRun on RTX
industries
AutomotiveGamingHealthcareIndustrialRobotics

Automotive

Terms of Use

|

Privacy Policy

|

Manage My Privacy

|

Contact

Copyright Ā© 2025 NVIDIA Corporation

AI Models for In-Vehicle Applications

Leverage AI models to improve embedded software for automotive applications, boosting efficiency and accelerating deployment.

PREVIEW

nvidiabevformer

Advanced transformer for multi-frame bird's-eye-view 3D perception in autonomous driving.

automotiveautonomous vehiclesbevperception
PREVIEW

nvidiasparsedrive

End-to-end autonomous driving stack integrating perception, prediction, and planning with sparse scene representations for efficiency and safety.

automotiveautonomous vehiclesav stackbev

Enterprise AI Models for Cloud Deployment

Leverage advanced AI models to streamline automotive software development and optimize cloud deployment.

Run Anywhere

nvidiacosmos-predict1-7b

Generalist model to generate future world state as videos from text and image prompts to create synthetic training data for robots and autonomous vehicles.

physical aiautonomous vehiclesimage-to-worldroboticstext-to-worldsynthetic data generation
PREVIEW

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.

physical aipolicy evaluationroboticssynthetic data generationvideo-to-world

nvidiacosmos-transfer1-7b

Generates physics-aware video world states for physical AI development using text prompts and multiple spatial control inputs derived from real-world data or simulation.

autonomous vehiclesphysical airoboticssynthetic data generationvideo-to-world
PREVIEW

microsoftphi-4-multimodal-instruct

Cutting-edge open multimodal model exceling in high-quality reasoning from image and audio inputs.

chart and table understandinglanguage generationspeech recognitionvisual qaimage-to-text
Run Anywhere

metallama-3.3-70b-instruct

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

instruction followingmathreasoningtext-to-textcode generation
Run Anywhere

metallama-3.1-405b-instruct

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

chatsynthetic data generationcode generation
Run Anywhere

deepseek-aideepseek-r1

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

mathadvanced reasoningchat
Run Anywhere

qwenqwen2.5-7b-instruct

Chinese and English LLM targeting for language, coding, mathematics, reasoning, etc.

chinese language generationlarge language modelstext-to-textchat
Run Anywhere

nvidianvclip

NV-CLIP is a multimodal embeddings model for image and text.

computer visionnvidia nimrun-on-rtxmultimodal embeddingstext and image
Run Anywhere

nvidiallama-3.2-nv-embedqa-1b-v2

Multilingual and cross-lingual text question-answering retrieval with long context support and optimized data storage efficiency.

embeddingnemo retrieverrun-on-rtxretrieval augmented generationtext-to-embedding
Run Anywhere

nvidiallama-3.2-nv-rerankqa-1b-v2

Fine-tuned reranking model for multilingual, cross-lingual text question-answering retrieval, with long context support.

nemo retrieverrerankingretrieval augmented generation
Run Anywhere

nvidiallama-3.1-nemoguard-8b-topic-control

Topic control model to keep conversations focused on approved topics, avoiding inappropriate content.

content safetydialogue safetyguard modelllm safety
Run Anywhere

nvidiallama-3.1-nemoguard-8b-content-safety

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

content safetyguard modelllm safetycontent moderation
Run Anywhere

nvidiacuopt

World-record accuracy and performance for complex route optimization.

route optimization
PREVIEW

nvidiausdvalidate

Verify compatibility of OpenUSD assets with instant RTX render and rule-based validation.

openusdusdvalidationvisualization 3ddigital twinsynthetic data generation

nvidiausdsearch

AI-powered search for OpenUSD data, 3D models, images, and assets using text or image-based inputs.

3dnvidia nimopenusdtext-to-3dusddigital twinsynthetic data generation
PREVIEW

nvidiausdcode

State-of-the-art LLM that answers OpenUSD knowledge queries and generates USD-Python code.

chatnvidia nimopenusdcode generationdigital twinsynthetic data generation
PREVIEW

googlegemma-3-27b-it

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

language generationvision assistantvisual question answeringimage-to-text
PREVIEW

nvidiavila

Multi-modal vision-language model that understands text/img/video and creates informative responses

vlmvision language modelimage captionimage to text
Run Anywhere

metallama-3.1-8b-instruct

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

chatlanguage generationrun-on-rtxtext-to-textcode generation
Run Anywhere

nvidiallama-3.1-nemotron-nano-4b-v1.1

State-of-the-art open model for reasoning, code, math, and tool calling - suitable for edge agents

edgemathreasoningtool calling
Run Anywhere

nvidiallama-3.3-nemotron-super-49b-v1

High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.

advanced reasoningfunction callinginstruction followingmath
Run Anywhere

nvidiallama-3.1-nemotron-70b-instruct

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

chatlanguage generationtext-to-textcode generation
PREVIEW

qwenqwq-32b

Powerful reasoning model capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems.

advanced reasoningcodingmathchat
PREVIEW

microsoftphi-4-mini-instruct

Lightweight multilingual LLM powering AI applications in latency bound, memory/compute constrained environments

chatlanguage generationtext-to-textcode generation
Run Anywhere

nvidianv-rerankqa-mistral-4b-v3

Multilingual text reranking model.

rerankingnemo retrieverretrieval augmented generation
Run Anywhere

nvidianv-embedqa-e5-v5

English text embedding model for question-answering retrieval.

embeddingnemo retrieverretrieval augmented generationtext-to-embedding
Run Anywhere

nvidianv-embedqa-mistral-7b-v2

Multilingual text question-answering retrieval, transforming textual information into dense vector representations.

embeddingretrieval augmented generationnemo retriever

Explore NVIDIA Automotive Blueprints

Comprehensive reference workflows that accelerate automotive software development with NVIDIA acceleration libraries, APIs, NIM, and microservices.

Enterprise

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.

blueprintenterprisenvidia omniverseindustrialomniverse blueprintsimulation
Enterprise

nvidiaBuild a Digital Twin for Interactive Fluid Simulation

This NVIDIA Omniverseā„¢ Blueprint demonstrates how commercial software vendors can create interactive digital twins.

blueprintcaecomputer-aided-engineeringexternal aerodynamicsenterprisenvidia omniversesimulation
Enterprise

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.

blueprintenterprisenvidia omniversesimulationvisual design
Enterprise

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