1. [Industries](/industries/overview) [Telecommunication](/industries/telecommunications) AI Aerial #### Open-Source NVIDIA AI Aerial NVIDIA AI Aerial software is now available as open source. This enables developers worldwide to access and modify the codebase, getting a head start on their AI-native 6G research and development. Click the link above to access. [Access](https://github.com/NVIDIA/aerial-cuda-accelerated-ran) # NVIDIA AI Aerial NVIDIA AI Aerial™ is a suite of accelerated computing platforms, software libraries, and tools to build, train, simulate, and deploy AI-native wireless networks. It enables developers and researchers to go from rapid prototyping to commercial development of AI-RAN solutions for 5G and 6G that telcos can deploy. [Get the Code](https://github.com/NVIDIA/aerial-cuda-accelerated-ran "Get the Code")[Read Documentation](https://docs.nvidia.com/aerial/index.html "Read Documentation")[Join 6G Developer Program ](/6g-program "Join 6G Developer Program") * * * ## NVIDIA AI Aerial Software Explore open-source software libraries and tools for building, training, simulating, and deploying AI-native wireless networks. Access to NVIDIA Aerial software is available on [GitHub](https://github.com/NVIDIA/aerial-cuda-accelerated-ran). Access for NVIDIA Sionna™ is available via the [Sionna Developer page](https://developer.nvidia.com/sionna). ### NVIDIA Sionna A GPU-accelerated, differentiable, open-source library for 5G and 6G communications research. It features a lightning-fast ray tracer for radio propagation, a link-level simulator, and system-level simulation capabilities. [Read Sionna Documentation](https://nvlabs.github.io/sionna/) ### NVIDIA Aerial Framework A framework for generating high-performance, CUDA®-accelerated 5G/6G pipelines from Python or MATLAB. It includes a runtime for executing the pipelines on NVIDIA Aerial™ RAN computer platforms. [Read Aerial Framework Documentation](https://docs.nvidia.com/aerial/#aerial-framework) ### NVIDIA Aerial CUDA-Accelerated RAN NVIDIA CUDA libraries for layer 1 (L1) and layer 2 (L2) RAN, to build commercial-grade and software-defined 5G and 6G radio access networks. [Read Aerial CUDA-Accelerated RAN Documentation](https://docs.nvidia.com/aerial/cuda-accelerated-ran/latest/index.html) ### NVIDIA Aerial Omniverse Digital Twin A platform that uses NVIDIA Omniverse™ to create next-generation network digital twins, enabling physically accurate virtual 5G and 6G wireless networks, from single towers to full cities. [Read Aerial Omniverse Digital Twin Documentation](https://docs.nvidia.com/aerial/aerial-dt/text/overview.html?ncid=em-news-547452-vt26) * * * ## Hardware Platforms #### NVIDIA AI Aerial Research Platforms These systems enable the building, training, and over-the-air testing of AI-native wireless innovations for 5G and 6G. ![img-alt-text](https://developer.download.nvidia.com/images/aerial/sionna-research-kit.jpg) #### Sionna Research Kit Built on an open-source foundation and powered by NVIDIA’s state-of-the-art, GPU-accelerated libraries, the Sionna Research Kit makes rapid prototyping, training, and deployment of cutting-edge 5G and 6G algorithms achievable for everyone—from seasoned professionals to students. [Learn More About Sionna Research Kit](https://nvlabs.github.io/sionna/rk/index.html) ![img-alt-text](https://developer.download.nvidia.com/images/aerial/arc-ota.jpg) #### Aerial Testbed (ARC-OTA) An end-to-end system that includes Aerial CUDA-Accelerated RAN combined with open-source software (OAI L2+ and 5G Core) running on NVIDIA GH200 or DGX Spark, over-the-air. Used for product development,, and performance optimization of commercial-grade and software-defined AI-RAN solutions. [Learn More About ARC-OTA](https://docs.nvidia.com/aerial/aerial-ran-colab-ota/current/index.html) #### NVIDIA AI Aerial Deployment Platforms The Aerial RAN Computer (ARC) family delivers high-performance, scalable, and accelerated computing platforms for telecom networks, enabling commercial AI-RAN deployments. ![NVIDIA Aerial RAN Computer-1](https://developer.download.nvidia.com/images/aerial/aerial-ran-computer-1.jpg) #### Aerial RAN Computer-1 A modular and high-performance AI-RAN platform for high-density deployments, suited for AI-centric workloads and designed to scale from distributed RAN (D-RAN) to centralized RAN (C-RAN) at mobile switching offices. [Learn More About Aerial RAN Computer-1](https://developer.nvidia.com/blog/bringing-ai-ran-to-a-telco-near-you/) ![NVIDIA ARC-Compact](https://developer.download.nvidia.com/images/aerial/arc-compact.jpg) #### ARC-Compact An energy-efficient and high-performance AI-RAN platform for cell sites, suited for RAN-centric workloads and designed to meet the form-factor and environmental requirements for distributed RAN deployments. [Learn More About ARC-Compact](https://developer.nvidia.com/blog/deploy-ai-ran-at-cell-sites-with-nvidia-arc-compact/) ![NVIDIA ARC-Pro](https://developer.download.nvidia.com/images/aerial/arc-pro(1).jpg) #### ARC-Pro A high-performance, energy-efficient AI-RAN platform featuring NVIDIA Blackwell RTX PRO™ GPUs, designed for on-ramping to AI-native 5G and 6G with advanced computing, connectivity, and sensing. Telco-optimized form factor, suitable for upgrading existing sites or greenfield deployments. [Learn More About ARC-Pro](https://resources.nvidia.com/en-us-aerial-ran-computer-pro) * * * ## Get Started With NVIDIA AI Aerial ### Build and Train Build and train AI/ML models for RAN, physical (PHY), and media access control (MAC) layers. - [Explore Sionna Documentation](https://nvlabs.github.io/sionna/) - [Access pyAerial Docs](https://docs.nvidia.com/aerial/archive/cuda-accelerated-ran/24-1/pyaerial/index.html) - [Learn About Aerial Data Lake](https://docs.nvidia.com/aerial/archive/cuda-accelerated-ran/24-1/aerial_data_lake/index.html) - [Begin With Aerial CUDA-Accelerated RAN](https://docs.nvidia.com/aerial/cuda-accelerated-ran/latest/index.html) - [Get Started With Aerial Framework](https://docs.nvidia.com/aerial/#aerial-framework) ### Simulate Run large-scale, photorealistic 5G and 6G wireless network scenarios - [Learn About Sionna SYS](https://nvlabs.github.io/sionna/sys/index.html) - [Use Sionna Ray-Tracing Guide](https://github.com/NVlabs/sionna-rt) - [Use Aerial Data Lake for Simulation Data](https://docs.nvidia.com/aerial/cuda-accelerated-ran/latest/aerial_data_lake/index.html) - [Learn About Aerial Omniverse Digital Twin](https://docs.nvidia.com/aerial/aerial-dt/text/overview.html?ncid=em-news-547452-vt26) - [Get Started With Aerial Omniverse Digital Twin](https://docs.nvidia.com/aerial/aerial-dt/text/installation.html#installation) ### Deploy Implement and validate in live and edge networks at scale. - [Order Sionna Research Kit](https://nvlabs.github.io/sionna/rk/quickstart.html) - [Refer to ARC-OTA Documentation](https://docs.nvidia.com/aerial/aerial-ran-colab-ota/current/index.html) - [Read About Aerial RAN Computer-1](https://developer.nvidia.com/blog/bringing-ai-ran-to-a-telco-near-you/) - [Learn About ARC-Compact](https://developer.nvidia.com/blog/deploy-ai-ran-at-cell-sites-with-nvidia-arc-compact/) - [Explore ARC-Pro](https://resources.nvidia.com/en-us-aerial-ran-computer-pro) * * * ## Learning Library Blog NVIDIA Open-Sources AI Aerial Libraries to Spark Wireless Network Development **NVIDIA AI Aerial** NVIDIA open-sources Aerial libraries, with Aerial Testbed and Sionna Research Kit now supported on NVIDIA DGX Spark for, developing AI algorithms for wireless. Tech Blog Introducing the NVIDIA Sionna Research Kit on DGX Spark **NVIDIA Sionna** The all-in-one open-source solution allows for the rapid prototyping of next-generation AI-native algorithms, training, and deployment in a real wireless network. Tech Blog Accelerated and Distributed UPF for the Era of Agentic AI and 6G **NVIDIA AI Aerial** A key enabler for 6G and AI-RAN is the distributed user plane function (dUPF), which enables ultra-low-latency, high-throughput, and distributed AI workloads. Tech Blog AI-RAN Goes Live and Unlocks a New AI Opportunity for Telcos **AI-RAN** SoftBank has turned their AI-RAN vision into reality with a successful outdoor field trial in Fujisawa City, Kanagawa, Japan. Tech Blog Deploy AI-RAN at Cell Sites With NVIDIA ARC-Compact **NVIDIA ARC-Compact** ARC-Compact brings AI-RAN to cell sites, enabling efficient, space-constrained, and power-constrained edge deployments. Tech Blog AODT Boosts Development of AI-Native Wireless **NVIDIA Aerial Omniverse Digital Twin** Aerial Omniverse Digital Twin is an AI-native digital twin platform built with NVIDIA Omniverse and designed for cutting-edge research and development of 5G and 6G wireless systems. * * * ## NVIDIA AI Aerial Ecosystem Academia and industry leaders are collaborating to advance AI-native wireless networks and drive 6G research. ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/1finity-fujitsu-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner - Aarna.mi](https://developer.download.nvidia.com/images/logos/aarna-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner - Amdocs](https://developer.download.nvidia.com/images/logos/amdocs-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner - Ansys](https://developer.download.nvidia.com/images/logos/endorsed-ansys-logos-full-color-rgb.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/gtc-dc-rgb-booz-allen-1250x703.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner - Cisco](https://developer.download.nvidia.com/images/logos/cisco-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/deepsig-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/dell-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/eth-zurich-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/hpe-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner - Insadot](https://developer.download.nvidia.com/images/logos/ioh-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/keysight-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/kyocera-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner - Mitre](https://developer.download.nvidia.com/images/logos/mitre-logo.svg.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/neu-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/nokia-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/odc-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner - Raydisys](https://developer.download.nvidia.com/images/logos/radisys-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/red-hat-color-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner - Rice University](https://developer.download.nvidia.com/images/logos/rice-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/rohde-schwarz-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner - Samsung](https://developer.download.nvidia.com/images/logos/samsung-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/softbank-logo(1).svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/sterling-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/supermicro-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner - SUTD](https://developer.download.nvidia.com/images/logos/sutd-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/t-mobile-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/oulu-logo.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner - University of Sheffield](https://developer.download.nvidia.com/images/logos/uni-sheffield.svg) ![NVIDIA AI Aerial Ecosystem and Industry partner -](https://developer.download.nvidia.com/images/logos/viavi-solutions-logo.svg) ## Next Steps ## Join the 6G Developer Program Get access to NVIDIA AI Aerial software resources. [Join Now](https://developer.nvidia.com/6g-program "Join Now") ## NVIDIA AI Aerial FAQ NVIDIA AI Aerial is a suite of accelerated computing platforms, software libraries, and tools for building, training, simulating, and deploying AI-native wireless networks. AI Aerial supports both advanced wireless research and commercial-grade cellular deployment. It enables developers to go from rapid prototyping to commercial development of AI-RAN solutions for 5G and 6G that telcos can deploy. AI Aerial includes a variety of hardware and software resources for wireless research and commercial deployment. Hardware ranges from small to large accelerated computing platforms, comprising various GPUs, CPUs and Networking components. Software libraries range from open-source Sionna for rapid prototyping to Aerial CUDA-Accelerated RAN, Aerial Framework and Aerial Omniverse Digital Twin for building CUDA-accelerated software-defined RAN. Developers and researchers can access Aerial CUDA-Accelerated RAN Aerial Framework on [GitHub](https://github.com/NVIDIA/aerial-cuda-accelerated-ran). Access Aerial Omniverse Digital Twin by joining the [NVIDIA 6G Developer Program](https://developer.nvidia.com/6g-program). For Sionna, access is available via the [Sionna Developer page](https://developer.nvidia.com/sionna). Documentation, SDKs, and hardware platforms are available for rapid onboarding and experimentation. Compatible hardware includes Aerial Testbed (ARC-OTA), Aerial RAN Computer-1, ARC-Compact, ARC-Pro, and the Sionna Research Kit. These are built using various accelerated computing platforms such as NVIDIA Jetson Orin, DGX Spark, Grace Hopper 200 for research and Grace Blackwell 300, L4 GPUs and RTX Pro GPUs for commercial deployments. AI Aerial supports centralized and distributed AI-RAN deployments for public and private 5G and future 6G networks. Aerial CUDA-Accelerated RAN is O-RAN 7.2x compliant and supports O-RAN Distributed Unit (O-DU) functionality.