NVIDIA

About NVIDIA

NVIDIA pioneered accelerated computing to tackle challenges no one else can solve. Our work in AI and digital twins is transforming the world's largest industries and profoundly impacting society.

Accelerated computing and AI have fully arrived. The acceleration of deep learning ignited the Big Bang of AI. Now, generative AI is a new computing platform, like the PC, internet, and mobile-cloud.

Credit: Runway AI, Adobe, Tabnine, WPP

Website ↗

Source ↗ · 2026-11-12T02:17:03.556571681Z

366 indexed models

366 matching models

Boltz2-NIM-microservice · azureml-nvidia v1

azureFoundry/azureml-nvidia/Boltz2-NIM-microservice@1

<!-- DO NOT CHANGE MARKDOWN HEADERS. IF CHANGED, MODEL CARD MAY BE REJECTED BY A REVIEWER --> <!-- `description.md` is required. --> ## Description Boltz-2 NIM is a next-generation structural biology foundation model that shows strong performance for both structure and affinity

Input modalities
text
Output modalities
text

canary-1b-asr

nvidiaNim/nvidia/canary-1b-asr

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

Capabilities
transcription

conformer-ctc-asr

nvidiaNim/nvidia/conformer-ctc-asr

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

Capabilities
transcription

cosmos3-nano-reasoner

nvidiaNim/nvidia/cosmos3-nano-reasoner

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

Capabilities
videoInput

Cosmos3-Super

vertexAI/publishers/nvidia/models/cosmos3-nano@cosmos3-super

Input modalities
text
Output modalities
text
Capabilities
audioInput, imageOutput, multimodal, videoOutput, visionInput

Cosmos3-Super-Image2Video

vertexAI/publishers/nvidia/models/cosmos3-nano@cosmos3-super-image2video

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

Cosmos3-Super-Text2Image

vertexAI/publishers/nvidia/models/cosmos3-nano@cosmos3-super-text2image

Input modalities
text
Output modalities
text

Benchmarks

  • LMArena: 1,149.71

Cosmos-reason1-NIM-microservice · azureml-nvidia v1

azureFoundry/azureml-nvidia/Cosmos-reason1-NIM-microservice@1

## Description ### [!] Attention Required : This model is being retired. Migrate your workloads to [Cosmos 3 Super](https://ai.azure.com/catalog/models/nvidia--cosmos3-super) NVIDIA Cosmos Reason – an open, customizable, 7B-parameter reasoning vision language model (VLM) for ph

Input modalities
video, image, text
Output modalities
text
Capabilities
multimodal, visionInput

cosmos-transfer2.5-2b

nvidiaNim/nvidia/cosmos-transfer2_5-2b

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.

CUDA-Autocomplete · HuggingFace v1

azureFoundry/HuggingFace/nvidia-cuda-autocomplete@1

`nvidia/CUDA-Autocomplete` powered by vLLM - [Original Model Card](https://huggingface.co/nvidia/CUDA-Autocomplete) - [vLLM Documentation](https://docs.vllm.ai/) ## Chat Completions API ### Send Request You can use cURL or any REST Client to send a request to the Azure ML end

Input modalities
text
Output modalities
text

cuopt

nvidiaNim/nvidia/nvidia-cuopt

World-record accuracy and performance for complex route optimization.

Deepseek-R1-Distill-Llama-8B-NIM-microservice · azureml-nvidia v1

azureFoundry/azureml-nvidia/Deepseek-R1-Distill-Llama-8B-NIM-microservice@1

DeepSeek AI has developed a range of distilled models based on Meta's Llama architectures, with sizes spanning from 1.5 to 70 billion parameters, starting from the foundation of DeepSeek-R1. This distillation process involves training smaller models to replicate the behavior and

Input modalities
text
Output modalities
text

Deepseek-R1-Distill-Llama-8B-NIM-microservice · azureml-nvidia v2

azureFoundry/azureml-nvidia/Deepseek-R1-Distill-Llama-8B-NIM-microservice@2

### [!] Attention Required : This model is being retired. Migrate your workloads to [Nemotron 3 Super](https://ai.azure.com/catalog/models/nvidia--nvidia-nemotron-3-super-120b-a12b-fp8) DeepSeek AI has developed a range of distilled models based on Meta's Llama architectures, wi

Input modalities
text
Output modalities
text

Earth-2 FourCastNet 3 · azureml-nvidia-ent v1

azureFoundry/azureml-nvidia-ent/earth2studio-fcn3@1

FourCastNet 3 is a global AI weather forcasting model. It was trained on ERA5 and provides forecasts at 6-hour intervals on a 0.25° equi-rectangular latitude/longitude grid.

Input modalities
geospatial
Output modalities
geospatial

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace