C-RADIOv2 Overview

Description:

Cradiov2 model card, nSpect, subcards C-RADIOv2 specializes in visual feature extraction. For instance, C-RADIOv2 generates image embeddings that can be used by a downstream model to classify images. The C-RADIOv2 models are available in multiple sizes:

• Base (90M parameters).
• Large (320M parameters).
• Huge (653M parameters).
• Gigantic (1.8B parameters).

C-RADIOv2 was trained for 1M steps (400k more steps than v1), using: Inverse frequency sampling for data balancing PHI Standardization for teacher distribution balance The model is ready for commercial and non-commercial use.

License/Terms of Use

License to use these models is covered by the NVIDIA Open Model License. By downloading the model, you accept the terms and conditions of these licenses.

Deployment Geography:

Global.

Use Case:

C-RADIOv2 is designed for developers and researchers to extract visual features at scale (via image embeddings) for image classification.

Release Date:

NGC 04/15/2025

References:

AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One
PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation
RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models

Model Architecture:

Architecture Type: Neural Network Network Architecture: Vision Transformer

This model has 4 versions:

• ViT-B: 90 million model parameters
• ViT-L: 320 million model parameters
• ViT-H: 653 million model parameters
• ViT-G: 1.8 billion model parameters

Input:

Input Type: Image
Input Format: Red, Green, Blue (RGB)
Input Parameters: Two Dimensional (2D)
Other Properties Related to Input: Image resolutions up to 2048x2028 in increments of 16 pixels

Output:

Output Type: Embeddings
Output Format: Tensor
Output Parameters: Two Dimensional (2D)
Other Properties Related to Output: Downstream model required to leverage image features

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

Software Integration:

Runtime Engine : TAO 6.0.0

Supported Hardware Microarchitecture Compatibility:

• NVIDIA Ampere
  
• NVIDIA Blackwell
  
• NVIDIA Jetson
  
• NVIDIA Hopper
  
• NVIDIA Lovelace
  
• NVIDIA Pascal
  
• NVIDIA Turing
  

Operating System(s):

• Linux

Model Version(s):

• C-RADIOv2-B (90M parameters).
• C-RADIOv2-L (320M parameters).
• C-RADIOv2-H (653M parameters).
• C-RADIOv2-G (1.8B parameters).

Training Dataset:

Training Dataset:

Data Collection Method by dataset
Automated

Labeling Method by dataset
Not Applicable (no labels are needed)

Properties
700 Million Image-Text pairs NV Internal Data

Methodology and KPI

​Benchmark

The key performance indicator is accuracy, following the standard evaluation protocol for image classification. The KPIs for the evaluation data are reported below:

Inference:

Engine: PyTorch

Test Hardware: A100

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please report security vulnerabilities or NVIDIA AI Concerns here.