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

nvidia/Cosmos3-Edge

huggingface/nvidia/Cosmos3-Edge

Capabilities
audioInput, imageOutput, multimodal, videoOutput, visionInput

nvidia/Cosmos3-Nano

huggingface/nvidia/Cosmos3-Nano

Capabilities
audioInput, imageOutput, multimodal, videoOutput, visionInput

nvidia/Cosmos-Reason1-7B

azureFoundry/azure-huggingface/nvidia--cosmos-reason1-7b@5

VLM for physical AI reasoning over text, images, and video.

Context window
128,000
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, visionInput

nvidia/CUDA-Autocomplete

vertexAI/publishers/hf-nvidia/models/cuda-autocomplete@001

Input modalities
text
Output modalities
text

nvidia/DeepSeek-R1-NVFP4

vertexAI/publishers/hf-nvidia/models/deepseek-r1-nvfp4@001

Input modalities
text
Output modalities
text

nvidia/EGM-4B

azureFoundry/HuggingFace/nvidia-egm-4b@2

`nvidia/EGM-4B` powered by vLLM - [Original Model Card](https://huggingface.co/nvidia/EGM-4B) - [vLLM Documentation](https://docs.vllm.ai/) > **⚠️ Warning**: `nvidia/EGM-4B` is a base model hence it doesn't have a pre-defined chat template as it's not fine-tuned for chat applic

Input modalities
text
Output modalities
text

nvidia/EGM-4B-SFT

azureFoundry/HuggingFace/nvidia-egm-4b-sft@1

`nvidia/EGM-4B-SFT` powered by vLLM - [Original Model Card](https://huggingface.co/nvidia/EGM-4B-SFT) - [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 endpoint with you

Input modalities
text
Output modalities
text

nvidia/EGM-8B

azureFoundry/HuggingFace/nvidia-egm-8b@1

`nvidia/EGM-8B` powered by vLLM - [Original Model Card](https://huggingface.co/nvidia/EGM-8B) - [vLLM Documentation](https://docs.vllm.ai/) > **⚠️ Warning**: `nvidia/EGM-8B` is a base model hence it doesn't have a pre-defined chat template as it's not fine-tuned for chat applic

Input modalities
text
Output modalities
text

nvidia/EGM-8B-SFT

azureFoundry/HuggingFace/nvidia-egm-8b-sft@1

`nvidia/EGM-8B-SFT` powered by vLLM - [Original Model Card](https://huggingface.co/nvidia/EGM-8B-SFT) - [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 endpoint with you

Input modalities
text
Output modalities
text

nvidia/GLM-5.1-NVFP4

azureFoundry/HuggingFace/nvidia-glm-5.1-nvfp4@1

`nvidia/GLM-5.1-NVFP4` powered by vLLM - [Original Model Card](https://huggingface.co/nvidia/GLM-5.1-NVFP4) - [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 endpoint wi

Input modalities
text
Output modalities
text

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