Achieves benchmark 5G vRAN performance on FR1 and FR2, with seamless orchestration between AI and RAN workloads
BARCELONA, Spain and SINGAPORE, March 02, 2026 (GLOBE NEWSWIRE) -- SynaXG today announced major technical breakthroughs in AI-native radio access networks, demonstrating concurrent operation of 5G FR1, 5G FR2 and AI workloads on NVIDIA AI-RAN platform with real-time, policy-driven GPU orchestration. The results confirm that software-defined, AI-native RAN can deliver carrier-grade performance and continuous 24x7 operation, ready for commercial deployment.
SynaXG achieved carrier-grade 5G FR1 performance on a single NVIDIA GH200 platform. The system simultaneously operated 20 x 100MHz 5G NR cells, delivering more than 36Gbps of aggregated throughput with sub-10 millisecond latency, while supporting up to 1,200 connected user equipment per cell. These results validate that a fully software-defined AI-RAN running on accelerated computing infrastructure can match the performance of best-in-class commercial 5G deployments, while enabling AI workloads to run concurrently on the same shared platform without compromising network KPIs.
SynaXG also achieved the world's first carrier-grade FR2 virtualized RAN implementation running concurrently with FR1 and AI workloads on a shared GPU platform. The system delivered high throughput with end-to-end latency as low as 5 milliseconds, meeting the performance requirements for dense urban and enterprise deployments. This milestone demonstrates that millimetre-wave RAN can be realized as a fully software-defined workload on accelerated infrastructure without compromising carrier-grade KPIs.
SynaXG's real-time orchestration software dynamically allocates, and switches Multi-Instance GPU (MIG) partitions based on live RAN and AI key performance indicators. GPU resources are continuously rebalanced across FR1 for coverage, FR2 for capacity and AI workloads without service interruption, enabling deterministic RAN performance while maximizing infrastructure utilization.
The AI-RAN system operated continuously, 24 hours a day, 7 days a week, under sustained load, validating the stability, scalability and operational resilience required for carrier environments. The results confirm that NVIDIA GPU-accelerated AI-RAN can maintain predictable performance while adapting dynamically to changing traffic conditions and workload demand.
SynaXG's AI-RAN platform is built on hardware and software stack leveraging NVIDIA AI Aerial platforms, enabling a software-defined, AI-native architecture that supports deterministic network performance alongside AI processing on shared GPU infrastructure.
Looking ahead, SynaXG is extending its AI-RAN platform to additional NVIDIA platforms, including NVIDIA DGX Spark, demonstrating the portability of its software-defined architecture. This write once, run anywhere approach across NVIDIA CUDA-based platforms accelerates innovation cycles and simplifies deployment at speed that has never been seen with traditional approaches.
In parallel, SynaXG continues to advance AI-for-RAN capabilities focused on network optimization and automation, spectral and energy efficiency, ISAC, distributed MIMO, ICIC, etc. SynaXG has been working with partners on AI agents that analyse real-time network conditions and service demand and take actions to enhance performance, energy efficiency and operational simplicity in AI-native networks.
“With the recent industry-leading breakthroughs, SynaXG has demonstrated that AI-RAN can deliver carrier-grade FR1 and FR2 performance with continuous 24x7 operation on shared NVIDIA AI infrastructure,” said Xin Huang, CEO of SynaXG. “Our software-defined approach enables operators and enterprises to deploy scalable, AI-native networks and are ready for commercial deployment.”
“Software-defined architecture is key to the next generation of wireless networks. SynaXG's benchmark 5G performance on NVIDIA AI-RAN platform proves that operators and enterprises can achieve the flexibility and agility of cloud-native computing while maintaining carrier-grade throughput and performance per watt, required for commercial 5G services”, said Soma Velayutham, VP of AI and Telecoms, NVIDIA.
SynaXG will showcase these AI-RAN breakthroughs as part of the AI-RAN Alliance Working Group 2 demonstrations at AI-RAN Alliance booth Hall 2, 2E45 and at the SynaXG booth at Hall 5, 5F21 Mobile World Congress 2026 in Barcelona.
About SynaXG
SynaXG is a Singapore-based technology company pioneering AI-native radio access networks (AI-RAN). Its unified software platform integrates 5G RAN and AI capabilities on shared commercial hardware, enabling operators, hyperscalers and enterprises to deploy high-performance, energy-efficient, and monetizable AI-driven networks. SynaXG works closely with global ecosystem partners across silicon, cloud, RAN and AI to accelerate the transition toward 5G-Advanced and 6G architectures.
For more information, visit www.synaxg.com
Watch the video accompanying this announcement on YouTube.
For additional context, see NVIDIA's AI-RAN on its corporate blog.
Media contact: media@synaxg.com
A video accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/e0e6c93a-fb23-4f53-9edb-f495916f1c41