Synaxg announced major milestones in artificial intelligence native radio access networks by running concurrent 5g fr1, 5g fr2 and artificial intelligence workloads on the nvidia artificial intelligence ran platform with real time, policy driven gpu orchestration. The company positions these results as proof that a software defined, artificial intelligence native ran can deliver carrier grade performance and continuous 24×7 operation suitable for commercial rollouts. The platform is built on the nvidia artificial intelligence aerial stack, combining radio access and artificial intelligence processing on shared gpu infrastructure.
In fr1 testing, 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. The implementation is fully software defined and runs as an artificial intelligence ran workload on accelerated computing infrastructure, which Synaxg says matches best in class commercial 5g performance while still allowing artificial intelligence workloads to run on the same hardware without degrading network kpis. In a parallel milestone, Synaxg reported what it calls the world’s first carrier grade fr2 virtualized ran implementation operating concurrently with fr1 and artificial intelligence workloads on a shared gpu platform, with end to end latency as low as 5 milliseconds for dense urban and enterprise scenarios.
Central to the architecture is Synaxg’s real time orchestration software, which dynamically allocates and switches multi instance gpu partitions based on live ran and artificial intelligence key performance indicators. GPU resources are continuously rebalanced across fr1 for coverage, fr2 for capacity and artificial intelligence workloads without service interruption, enabling deterministic ran performance while maximizing infrastructure utilization. The artificial intelligence ran system operated continuously, 24 hours a day, 7 days a week, under sustained load, which is presented as evidence of the stability, scalability and resilience required by operators. Synaxg is extending its platform to additional nvidia systems, including nvidia dgx spark, following a write once, run anywhere approach on cuda based hardware, while also advancing artificial intelligence for ran capabilities such as network optimization, automation, spectral and energy efficiency, and artificial intelligence agents that analyse real time conditions and act to improve performance. Company executives from Synaxg and nvidia framed software defined architecture and artificial intelligence ran as key to next generation wireless networks, with live demonstrations planned at mobile world congress 2026 in barcelona.
