With the proliferation of AI-driven services, mobile networks call for superior performance and smarter automation. Ericsson, on June 11, 2026, went on to announce AI in RAN, which happens to be a software subscription offering telco-grade AI models that operate inside basebands as well as radios to improve efficiencies and performance as well as energy savings. This commercially scalable offering provides direct benefits for 5G networks of communications service providers – CSPs and enables the move to AI-native RAN with no additional hardware.
Introducing Ericsson AI in RAN
- AI models for telcos designed to run in real time inside the radio access network – RAN
- High-quality data for persistent learning software at scale.
- Agentic AI support to help with advanced RAN automation as well as network operations
According to Head of Networks Strategy & Product Management at Ericsson, Mårten Lerner, “Ericsson is redefining what’s possible in mobile networks by bringing powerful AI capabilities to service providers. With AI in RAN software, we are taking a major step toward AI-native networks, alongside the AI-ready radios we unveiled in February.”
The telco-grade AI models from Ericsson are optimized for ultra-low latency estimation in the microsecond range, with high robustness and dependability in varied and dynamic RAN environments. These models combine deep domain knowledge with training in terms of high-quality data, setting new standards as far as performance and efficiency are concerned.
Lerner adds that “service providers need networks that are high-performing, secure, and efficient in the AI era. With AI in RAN, Ericsson is bringing AI into networks to elevate 5G performance and efficiency through energy-efficient AI inference at scale.”
Have Been Proven in Commercial network deployments
Ericsson AI in RAN works along with Ericsson 5G Advanced on both purpose-built as well as cloud RAN platforms so as to unlock new AI-powered services. It represents the realization of the AI from the company for networks’ vision, using AI to improve the performance and productivity of networks. The aim for AI in RAN is to employ the right AI model in the correct section of the radio network, with Ericsson Silicon to drive energy-efficient AI inference within radios, and the most recent versions of RAN Compute and the portability of cloud RAN software mean AI capabilities can be implemented across partner platforms.
It is well to be noted that the first AI in RAN features will be available in Q2 2026, with additional enhancements coming later in 2026 itself. Software features involve AI-powered macro positioning, an AI-native scheduler for link adaptation, AI-managed beamforming, performance management event schema files, AI-powered multi-layer coordination, and augmented observability for AI in RAN.
AI in RAN from Ericsson is indeed proven in over 15 deployments and trials throughout the globe, offering up to 20% higher downlink speed and up to 10% better spectral performance. It also enables as much as 2x more high-traffic users, 90-95% accuracy of predictions of coverage, and almost 5x greater accuracy of user positioning.
As per Senior Vice President & CNO, SoftBank Corp., Teruyuki Oya, “Ericsson’s AI in RAN software marks an important step in bringing AI deeper into the radio access network. By enabling real-time optimization of radio performance, spectrum efficiency and user experience, it helps us turn AI innovation into practical value on live networks. We also see strong potential in how this foundation can support emerging AI-driven services, including physical AI scenarios that depend on low-latency, highly reliable connectivity and intelligent coordination between network and compute resources.”
Remarks Senior Vice President, Network Technology & Operations for Bell, Bruce Dean, “At Bell, we’re continuously evolving our network to meet growing demand for high-performance, AI-driven services. Integrating AI directly into the RAN is an important step in making networks more intelligent and efficient. Working with partners like Ericsson, we’re bringing these capabilities into our network to enhance performance, improve energy efficiency, and deliver a better experience for our customers.”
According to Head of Network Technology Office, SK Telecom, Yu Takki, “Through our collaboration with Ericsson, SK Telecom is advancing AI-RAN to enhance network performance and energy efficiency while supporting more intelligent and automated operations. By combining research, real-world validation, and software innovation, we aim to strengthen our leadership in AI-powered network evolution and help lay the foundation for AI-native 6G.”
The Chief Technology Officer at Rogers, Mark Kennedy, opines that “As Canada’s best 5G+ network, we’re proud to work with Ericsson and bring the latest 5G technology to Canadians. AI in RAN will help optimize network performance for customers in real-time and reduce energy consumption.”
Principal Analyst at Mobile Experts, Joe Madden, says that “This could be the best ROI for mobile operators in years. With a software upgrade, operators can squeeze more capacity, better observability, and more accurate location-based services out of the 5G network they bought years ago.”
Interestingly, Ericsson has embedded AI functionality throughout its products since 4G while also adding AI-ready acceleration in RAN Compute in 2021. In February 2026, the company launched neural network accelerators in its massive MIMO radios, boosting AI inference power by 10x.