5G and 6G Solutions
Transform Your Wireless Network With AI-RAN
Enable the onramp from 5G to 6G networks with software-defined architecture that fuses RAN and AI workloads on a common infrastructure to power AI-native air interface and edge AI applications.
Overview
Cellular Networks for the AI Era
In addition to voice, data, and video, wireless networks now need to support AI traffic generated by smartphones, cameras, robots, drones, smart glasses, AI agents, and more. This requires a new architecture to deliver super fast AI inferencing at scale with guaranteed quality of service, power AI algorithms to improve spectral efficiency, and support new edge AI applications. NVIDIA AI Aerial makes it possible, with a software-defined, accelerated platform to power RAN and AI from the same infrastructure, enabling telecommunication service providers to support AI today while future-proofing for 6G.
Benefits
One Accelerated Infrastructure for AI and RAN
Unlock New AI Applications and Services
NVIDIA AI Aerial provides accelerated compute for new AI applications and services. CSPs can monetize this today with AI factories, AI Grid, and host their own generative AI applications, or leverage NVIDIA AI Enterprise to build new AI offerings.
Maximize Resource Utilization
NVIDIA AI Aerial supports dynamic allocation of 5G and AI workloads based on demand within the same GPU. This increases capacity utilization by 2–3x and improves energy efficiency while reducing operational overhead of siloed infrastructure.
Boost Radio Performance
NVIDIA AI Aerial provides advanced Layer 1 (L1) and Layer 2 (L2) AI algorithms to improve spectral efficiency, which means CSPs can support many more connections while also improving performance.
Prepare for AI-Native 6G
With NVIDIA AI Aerial, CSPs can move to 6G with a software upgrade. Thanks to a fully software-defined architecture, new capabilities are added through continuous software innovation, not hardware swaps.
One Extensible Architecture
NVIDIA AI Aerial provides a homogenous reference architecture for public and private 5G/6G networks, including support for Open-RAN, Centralized-RAN, Distributed-RAN, and Cloud-RAN.
Key Components
Building Blocks of the NVIDIA AI Aerial Platform
NVIDIA AI Aerial is a comprehensive suite of hardware and software components, underpinned by a fully software-defined architecture that enables easy scale-up, scale-out, and multi-tenancy to deliver AI-and-RAN, AI-for-RAN, and AI-on-RAN.
Use Cases
How NVIDIA AI Aerial Supports Network Services
Explore how a multi-purpose, accelerated AI-RAN infrastructure supports current and future industry use cases, driving business outcomes for telcos.
-
vRAN Deployments
-
AI and Generative AI Applications
-
6G Research and Development
-
Containerized Network Functions
-
AI Grid
One Software-Defined Architecture for Any vRAN Deployment
NVIDIA AI Aerial enables software-defined RAN by leveraging GPU acceleration and AI algorithms to supercharge RAN network performance. CSPs can use NVIDIA AI Aerial to deploy any virtual RAN variant—including 5G vRAN, Open RAN (O-RAN), private 5G, all the way to AI-native 6G.
Independent software vendors can also take the NVIDIA AI Aerial CUDA®-accelerated vRAN implementation and customize it with their own enhancements to create new vRAN products for different market segments and deployment scenarios.
AI and Generative AI Applications
From improving customer experiences and optimizing complex network operations with generative and agentic AI to extracting business insights with data science, CSPs are unlocking new ways to positively impact their bottom line. NVIDIA AI Aerial lets AI applications run on the same AI-RAN infrastructure and support CSPs’ internal use cases.
With NVIDIA AI Enterprise and NVIDIA NIM™, a suite of prepackaged AI modules and libraries, CSPs can also build their own AI and generative AI offerings and deliver them to their customers over a common AI-RAN infrastructure.
AI-Native 6G Research and Development
NVIDIA AI Aerial enables 6G research across all layers in the RAN stack. New AI and machine learning-based algorithms for L1 and L2 can be rapidly developed, simulated, and verified in the real world using real-time, over-the-air testbeds.
Developers can leverage NVIDIA open-source libraries and assemble synthetic and real-world datasets to train and simulate wireless networks—from link level to system level and from cell site to city scale.
Containerized Network Functions
The NVIDIA AI Aerial platform can be used to accelerate any containerized network function, including vRAN DU, centralized unit (CU), user plane function (UPF), radio intelligent controller (RIC), virtual router (vRouter), network security, and more. This approach maximizes resource utilization and energy efficiency and reduces total cost of ownership (TCO) compared to running siloed infrastructure for each network function.
The extensible architecture also allows ecosystem partners or CSPs to bring their own containerized network functions, leveraging accelerated compute and software stack from the AI Aerial platform.
AI Grid
CSPs are uniquely positioned to expand their data centers to build sovereign AI infrastructure and empower local governments, enterprises, and startups to build, develop, and deploy AI within national borders.
With NVIDIA AI Aerial, CSPs can turn their distributed mobile switching offices (MSOs) and cell sites into an AI Grid that can process AI workloads—including inference—wherever it makes the most sense, optimizing for the cost, speed, and performance needed for each type of workload. The AI Grid becomes an extension of the sovereign AI infrastructure, enabling new monetization opportunities such as GPU-as-a-service or AI-as-a-service.
NVIDIA’s State of AI in Telecom 2025 Report
Dive into the data compiled from a survey of over 450 telecom professionals from around the world. This year’s results show 37% cited network planning and operations, including AI-RAN, as an investment priority. Another 33% said they’re investing in AI for field operations optimization. Future areas of investment include using AI to monetize 5G and boosting R&D of 6G networks.
Ecosystem
Driving Network Transformation
Leaders from across the telecom industry are collaborating on cellular networks for the AI era.
Resources
Learn More About the NVIDIA AI Aerial Platform
Browse the latest news, blogs, and demos.