NVIDIA

nvidiaparakeet-1.1b-rnnt-multilingual-asr
High accuracy and optimized performance for transcription in 25 languages

nvidiallama-3.1-nemotron-ultra-253b-v1
Superior inference efficiency with highest accuracy for scientific and complex math reasoning, coding, tool calling, and instruction following.

nvidiacosmos-predict1-7b
Generates physics-aware video world states from text and image prompts for physical AI development.

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.

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

nvidiallama-3.3-nemotron-super-49b-v1
High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.

nvidiallama-3.1-nemotron-nano-8b-v1
Leading reasoning and agentic AI accuracy model for PC and edge.

nvidiamagpie-tts-multilingual
Natural and expressive voices in multiple languages. For voice agents and brand ambassadors.

nvidianv-embedcode-7b-v1
The NV-EmbedCode model is a 7B Mistral-based embedding model optimized for code retrieval, supporting text, code, and hybrid queries.

nvidianemoretriever-table-structure-v1
Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

nvidianemoretriever-graphic-elements-v1
Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

nvidianemoretriever-page-elements-v2
Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

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

nvidiacanary-1b-asr
Multi-lingual model supporting speech-to-text recognition and translation.

nvidiacanary-0.6b-turbo-asr
Multi-lingual model supporting speech-to-text recognition and translation.

nvidiallama-3.1-nemoguard-8b-topic-control
Topic control model to keep conversations focused on approved topics, avoiding inappropriate content.

nvidianemoguard-jailbreak-detect
Industry leading jailbreak classification model for protection from adversarial attempts

nvidiallama-3.1-nemoguard-8b-content-safety
Leading content safety model for enhancing the safety and moderation capabilities of LLMs


nvidiacosmos-nemotron-34b
Multi-modal vision-language model that understands text/img/video and creates informative responses

nvidiallama-3.2-nv-embedqa-1b-v2
Multilingual and cross-lingual text question-answering retrieval with long context support and optimized data storage efficiency.

nvidiallama-3.2-nv-rerankqa-1b-v2
Fine-tuned reranking model for multilingual, cross-lingual text question-answering retrieval, with long context support.

nvidianv-yolox-page-elements-v1
Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

nvidiaaudio2face-3d
Converts streamed audio to facial blendshapes for realtime lipsyncing and facial performances.

nvidiaconformer-ctc-asr
Automatic speech recognition model that transcribes speech in lower case English with record-setting accuracy and performance

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

nvidianemotron-4-mini-hindi-4b-instruct
A bilingual Hindi-English SLM for on-device inference, tailored specifically for Hindi Language.

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.

nvidiastudiovoice
Enhance speech by correcting common audio degradations to create studio quality speech output.

nvidiamistral-nemo-minitron-8b-8k-instruct
State-of-the-art small language model delivering superior accuracy for chatbot, virtual assistants, and content generation.

nvidiallama-3.1-nemotron-70b-reward
Leaderboard topping reward model supporting RLHF for better alignment with human preferences.

nvidiallama-3.1-nemotron-51b-instruct
Unique language model that delivers an unmatched accuracy-efficiency performance.

nvidiaconsistory
Generates consistent characters across a series of images without requiring additional training.

nvidianemotron-mini-4b-instruct
Optimized SLM for on-device inference and fine-tuned for roleplay, RAG and function calling

nvidiamistral-nemo-minitron-8b-base
State-of-the-art small language model delivering superior accuracy for chatbot, virtual assistants, and content generation.

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

nvidiaradtts-hifigan-tts
Natural, high-fidelity, English voices for personalizing text-to-speech services and voiceovers

nvidiamegatron-1b-nmt
Enable smooth global interactions in 36 languages.

nvidiafastpitch-hifigan-tts
Expressive and engaging English voices for Q&A assistants, brand ambassadors, and service robots

nvidiaparakeet-ctc-1.1b-asr
Record-setting accuracy and performance for English transcription.

nvidiaparakeet-ctc-0.6b-asr
State-of-the-art accuracy and speed for English transcriptions.

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

nvidiaaudio2face-2d
Create facial animations using a portrait photo and synchronize mouth movement with audio.

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

nvidianv-rerankqa-mistral-4b-v3
Multilingual text reranking model.

nvidianv-embedqa-e5-v5
English text embedding model for question-answering retrieval.

nvidianv-embedqa-mistral-7b-v2
Multilingual text question-answering retrieval, transforming textual information into dense vector representations.


nvidiallama3-chatqa-1.5-70b
Advanced LLM to generate high-quality, context-aware responses for chatbots and search engines.

nvidiallama3-chatqa-1.5-8b
Advanced LLM to generate high-quality, context-aware responses for chatbots and search engines.

nvidianemotron-4-340b-reward
Grades responses on five attributes helpfulness, correctness, coherence, complexity and verbosity.

nvidianemotron-4-340b-instruct
Creates diverse synthetic data that mimics the characteristics of real-world data.


nvidianv-embed-v1
Generates high-quality numerical embeddings from text inputs.

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

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

nvidiaembed-qa-4
GPU-accelerated generation of text embeddings used for question-answering retrieval.

nvidiarerank-qa-mistral-4b
GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.

nvidiadeepvariant
Run Google's DeepVariant optimized for GPU. Switch models for high accuracy on all major sequencers.

