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.

Model

Synthetic Data Generation

1mo

NVIDIA

Downloadable

llama-nemotron-embed-vl-1b-v2

Multimodal question-answer retrieval representing user queries as text and documents as images.

Model

nemo retriever

9.31M

2mo

NVIDIA

Free Endpoint

nemotron-content-safety-reasoning-4b

A context‑aware safety model that applies reasoning to enforce domain‑specific policies.

Model

NeMo Guardrails

280K

2mo

NVIDIA

Downloadable

cosmos-reason2-8b

Vision language model that excels in understanding the physical world using structured reasoning on videos or images.

Model

video understanding

68.6K

3mo

NVIDIA

Downloadable

nemoretriever-page-elements-v3

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

Model

Object Detection

75.53K

4mo

NVIDIA

Downloadable

nemotron-3-nano-30b-a3b

Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more

Model

MoE

12.84M

4mo

NVIDIA

Free Endpoint

riva-translate-4b-instruct-v1_1

Translation model in 12 languages with few-shots example prompts capability.

Model

nvidia nim

198K

4mo

NVIDIA

Free Endpoint

streampetr

StreamPETR offers efficient 3D object detection for autonomous driving by propagating sparse object queries temporally.

Model

autonomous vehicles

22.2K

5mo

NVIDIA

Downloadable

nemotron-parse

Cutting-edge vision-language model exceling in retrieving text and metadata from images.

Model

text and table extraction

295K

5mo

NVIDIA

Downloadable

nemotron-nano-12b-v2-vl

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

Model

language generation

4.73M

5mo

NVIDIA

Free Endpoint

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

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

Model

content moderation

121K

5mo

NVIDIA

Downloadable

parakeet-ctc-0.6b-zh-tw

Record-setting accuracy and performance for Mandarin Taiwanese English transcriptions.

Model

ASR

143

6mo

NVIDIA

Downloadable

llama-3_2-nemoretriever-300m-embed-v2

Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.

Model

Text-to-Embedding

137

6mo

NVIDIA

Downloadable

parakeet-ctc-0.6b-zh-cn

Record-setting accuracy and performance for Mandarin English transcriptions.

Model

ASR

3.35K

7mo

NVIDIA

Downloadable

parakeet-ctc-0.6b-es

Accurate and optimized Spanish English transcriptions with punctuation and word timestamps.

Model

ASR

7mo

NVIDIA

Downloadable

parakeet-ctc-0.6b-vi

Accurate and optimized Vietnamese-English transcriptions with punctuation and word timestamps.

Model

ASR

198

7mo

NVIDIA

Downloadable

nvidia-nemotron-nano-9b-v2

High‑efficiency LLM with hybrid Transformer‑Mamba design, excelling in reasoning and agentic tasks.

Model

thinking budget

365K

8mo

NVIDIA

Downloadable

nemoretriever-ocr-v1

Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.

Model

Table Extraction

687K

8mo

NVIDIA

Downloadable

parakeet-tdt-0.6b-v2

Accurate and optimized English transcriptions with punctuation and word timestamps

Model

ASR

1.62K

8mo

NVIDIA

Downloadable

llama-3.3-nemotron-super-49b-v1.5

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

Model

math

2.81M

8mo

NVIDIA

Free Endpoint

llama-3_2-nemoretriever-300m-embed-v1

Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.

Model

Text-to-Embedding

361K

8mo

NVIDIA

Downloadable

nemoretriever-ocr

Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.

Model

Table Extraction

20.2K

8mo

NVIDIA

DeprecatedFree Endpoint

magpie-tts-flow

Expressive and engaging text-to-speech, generated from a short audio sample.

Model

TTS

1.08K

9mo

NVIDIA

Downloadable

riva-translate-1.6b

Enable smooth global interactions in 36 languages.

Model

Neural machine translation

28.88K

9mo

NVIDIA

Downloadable

llama-3.2-nemoretriever-500m-rerank-v2

GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.

Model

nemo retriever

7.09K

9mo

NVIDIA

Free Endpoint

cosmos-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.

Model

Synthetic Data Generation

213

9mo

NVIDIA

Downloadable

Background Noise Removal

Removes unwanted noises from audio improving speech intelligibility.

Model

Nvidia Maxine

457

10mo

NVIDIA

Deprecation in 5dDownloadable

llama-3.2-nemoretriever-1b-vlm-embed-v1

Multimodal question-answer retrieval representing user queries as text and documents as images.

Model

nemo retriever

194K

9mo

NVIDIA

Downloadable

llama-3.1-nemotron-nano-vl-8b-v1

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

Model

doc intelligence

9.35M

9mo

NVIDIA

Free Endpoint

magpie-tts-zeroshot

Expressive and engaging text-to-speech, generated from a short audio sample.

Model

TTS

1.81K

10mo

NVIDIA

Downloadable

parakeet-1.1b-rnnt-multilingual-asr

High accuracy and optimized performance for transcription in 25 languages

Model

Automatic Speech Recognition

2.82K

11mo

NVIDIA

Deprecation in 3dDownloadable

llama-3.1-nemotron-ultra-253b-v1

Superior inference efficiency with highest accuracy for scientific and complex math reasoning, coding, tool calling, and instruction following.

Model

math

6.68M

9mo

NVIDIA

Free Endpoint

cosmos-predict1-5b

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

Model

Synthetic Data Generation

886

NVIDIA

Free Endpoint

sparsedrive

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

Model

autonomous vehicles

9mo

NVIDIA

Free Endpoint

bevformer

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

Model

autonomous vehicles

101

9mo

NVIDIA

Downloadable

llama-3.3-nemotron-super-49b-v1

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

Model

math

1.4M

9mo

NVIDIA

Downloadable

llama-3.1-nemotron-nano-8b-v1

Leading reasoning and agentic AI accuracy model for PC and edge.

Model

math

776K

9mo

NVIDIA

Downloadable

magpie-tts-multilingual

Natural and expressive voices in multiple languages. For voice agents and brand ambassadors.

Model

TTS

36.23K

9mo

NVIDIA

Free Endpoint

nv-embedcode-7b-v1

The NV-EmbedCode model is a 7B Mistral-based embedding model optimized for code retrieval, supporting text, code, and hybrid queries.

Model

nemo retriever

206K

10mo

NVIDIA

Downloadable

nemoretriever-table-structure-v1

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

Model

Object Detection

27.14K

NVIDIA

Downloadable

nemoretriever-graphic-elements-v1

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

Model

Object Detection

4.63K

NVIDIA

Downloadable

nemoretriever-page-elements-v2

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

Model

Object Detection

70.81K

NVIDIA

Downloadable

nemoretriever-parse

Cutting-edge vision-language model exceling in retrieving text and metadata from images.

Model

optical character recognition

105K

10mo

NVIDIA

Downloadable

canary-1b-asr

Multi-lingual model supporting speech-to-text recognition and translation.

Model

Automatic Speech Recognition

2.87K

NVIDIA

Downloadable

llama-3.1-nemoguard-8b-topic-control

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

Model

nemo guardrails

125K

NVIDIA

Downloadable

nemoguard-jailbreak-detect

Industry leading jailbreak classification model for protection from adversarial attempts

Model

nemo guardrails

56.19K

9mo

NVIDIA

Downloadable

llama-3.1-nemoguard-8b-content-safety

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

Model

nemo guardrails

142K

NVIDIA

Downloadable

genmol

Fragment-Based Molecular Generation by Discrete Diffusion.

Model

Chemistry

5.33K

9mo

NVIDIA

Downloadable

llama-3.2-nv-embedqa-1b-v2

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

Model

nemo retriever

2.37M

9mo

NVIDIA

Downloadable

llama-3.2-nv-rerankqa-1b-v2

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

Model

nemo retriever

178K

9mo

NVIDIA

Free Endpoint

usdcode

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

Model

Digital Twin

9mo

NVIDIA

Downloadable

nv-yolox-page-elements-v1

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

Model

Object Detection

1.28K

9mo

NVIDIA

Downloadable

conformer-ctc-asr

Automatic speech recognition model that transcribes speech in lower case Spanish with record-setting accuracy and performance

Model

ASR

NVIDIA

Downloadable

fourcastnet

FourCastNet predicts global atmospheric dynamics of various weather / climate variables.

Model

Weather Simulation

2.15K

NVIDIA

DeprecatedFree Endpoint

nemotron-4-mini-hindi-4b-instruct

A bilingual Hindi-English SLM for on-device inference, tailored specifically for Hindi Language.

Model

Indic

361K

11mo

NVIDIA

DownloadableFree Endpoint

studiovoice

Enhance input speech recorded with low-quality microphones in noisy or reverberant environments, producing studio-quality speech.

Model

communications

539

10mo

NVIDIA

Free Endpoint

nemotron-mini-4b-instruct

Optimized SLM for on-device inference and fine-tuned for roleplay, RAG and function calling

Model

Chat

197K

NVIDIA

DeprecatedFree Endpoint

mistral-nemo-minitron-8b-base

State-of-the-art small language model delivering superior accuracy for chatbot, virtual assistants, and content generation.

Model

language generation

3.16K

NVIDIA

DeprecatedFree Endpoint

nv-dinov2

NV-DINOv2 is a visual foundation model that generates vector embeddings for the input image.

Model

computer vision

891K

NVIDIA

DeprecatedFree Endpoint

nv-grounding-dino

Grounding dino is an open vocabulary zero-shot object detection model.

Model

Object Detection

6.19K

NVIDIA

Downloadable

megatron-1b-nmt

Enable smooth global interactions in 36 languages.

Model

Neural machine translation

NVIDIA

Downloadable

parakeet-ctc-1.1b-asr

Record-setting accuracy and performance for English transcription.

Model

ASR

61.24K

9mo

NVIDIA

Downloadable

parakeet-ctc-0.6b-asr

State-of-the-art accuracy and speed for English transcriptions.

Model

ASR

2.66K

10mo

NVIDIA

DeprecatedFree Endpoint

usdsearch

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

Model

Digital Twin

771

NVIDIA

Deprecation in 26dDownloadable

eyecontact

Estimate gaze angles of a person in a video and redirect to make it frontal.

Model

telepresence

1.65K

NVIDIA

Free Endpoint

usdvalidate

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

Model

Validation

1.04K

NVIDIA

Downloadable

nv-embedqa-e5-v5

English text embedding model for question-answering retrieval.

Model

Embedding

12.15M

9mo

NVIDIA

DeprecatedDownloadable

maisi

MAISI is a pre-trained volumetric (3D) CT Latent Diffusion Generative Model.

Model

Image Generation

983

NVIDIA

Downloadable

nvclip

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

Model

Computer vision

92.15K

10mo

NVIDIA

DeprecatedFree Endpoint

ocdrnet

OCDNet and OCRNet are pre-trained models designed for optical character detection and recognition respectively.

Model

Optical Character Recognition

905

NVIDIA

Free Endpoint

nv-embed-v1

Generates high-quality numerical embeddings from text inputs.

Model

Non-Commercial Use Only

4.48M

9mo

NVIDIA

DeprecatedFree Endpoint

visual-changenet

Visual Changenet detects pixel-level change maps between two images and outputs a semantic change segmentation mask

Model

image

526

NVIDIA

DeprecatedFree Endpoint

retail-object-detection

EfficientDet-based object detection network to detect 100 specific retail objects from an input video.

Model

Object Detection

472

NVIDIA

Free Endpoint

rerank-qa-mistral-4b

GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.

Model

Ranking

407K

NVIDIA

Downloadable

vista-3d

VISTA-3D is a specialized interactive foundation model for segmenting and anotating human anatomies.

Model

Interactive Annotation

1.12K

12mo

NVIDIA

Downloadable

molmim

MolMIM performs controlled generation, finding molecules with the right properties.

Model

Chemistry

215K

9mo

NVIDIA

Downloadable

cuopt

World-record accuracy and performance for complex route optimization.

Model

Route Optimization

33.13K

11mo

Your Privacy Choices

Contact