Home Compute and servers LinuxONE IBM Telum processor family for IBM LinuxONE
Advancing the future of mission-critical workloads with the next-generation IBM Telum chip
What's new Read the blog
Product picture of a Telum microchip

The Telum® chip is an advanced processor designed to power IBM LinuxONE 4 systems, which are tailored for organizations running Linux-based workloads that demand security, reliability and scalability, all within an energy-efficient footprint.

Built with integrated AI acceleration, industry-leading security and optimized performance, the Telum chip empowers organizations to unlock new possibilities for AI, cloud and data-driven operations-all with the resilience and sustainability that LinuxONE is known for. This next-generation chip showcases innovations, setting a new standard for enterprise computing by delivering unprecedented speed and efficiency for complex data environments through:

  • Integrated AI for real-time insights
  • Enhanced security and confidential computing
  • Reliability and continuous availability
  • Energy efficiency
  • High performance
  • Optimized for hybrid cloud and multicloud
Introducing IBM Telum II Processor and Spyre Accelerator

Welcome IBM Telum II processor and Spyre Accelerator™1, built for high-speed inferencing and ensemble AI. Get faster insights, solutions and time-to-value across your business with AI acceleration built to run where it is needed most—at the source of your data. 

Built to deliver deep learning and foundation model capabilities by using a multimodel ensemble method that focuses on performance and accuracy, this next-generation AI acceleration allows clients to use increasingly larger, more complex models for in-transaction workloads as well as certain generative AI use cases. 

The Telum II and Spyre Accelerator are expected to be available in 2025.

Meet the processors

First generation Telum The IBM Telum processor is a 7-nm microprocessor designed to deliver AI-driven insights without sacrificing response time in high-volume transactional workloads. It features 8 cores, each clocked over 5GHz and supported by a 32-MB private L2 cache, which combines to form a 256-MB virtual L3 and a 2-GB L4 cache. With 1.5x more cache per core than its predecessor, Telum boosts per-thread performance and overall capacity, helping ensure rapid response times for complex transactions, especially when enhanced by real-time AI inference. Read the blog

Second generation Telum II The new IBM Telum II Processor offers a built-in low-latency data processing unit (DPU) for accelerated IO. The main processor contains 4 interconnected core clusters, each with 8 programmable micro-controller cores. This helps ensure there is cache coherency among the 32 cores. Also, with 10, 36 MB Level-2 caches on the chip, one per core, one for the DPU and the 10th as the overall chip cache capacity(2). Also, there is a larger pool of virtual L3 and virtual L4 cache that are also turned into meaningful performance improvements. Each has grown by 40% in Telum II, to 360 MB and 2.8 GB(3).

Processor features AI acceleration

The Telum chip integrates AI acceleration directly into the processor, enabling real-time inferencing and analytics on transactional data without the need for more hardware. With an optimized Matrix Multiplication Engine for deep learning and machine learning tasks, the chip processes AI workloads faster, allowing organizations to run AI models on the chip itself for immediate insights during transactions—ideal for use cases like fraud detection, risk management and predictive analytics.

Explore AI on IBM LinuxONE
Integrated security

The Telum chip provides comprehensive end-to-end encryption, helping ensure that data is protected at rest, in transit and even while in use. Its confidential computing capabilities keep data encrypted during processing, safeguarding sensitive workloads in real-time. With quantum-safe cryptography, the chip is prepared to defend against future quantum computing threats, helping ensure long-term data security. Also, tamper detection mechanisms are built into the hardware, identifying and preventing unauthorized access or alterations, further enhancing security for critical applications.

Resilience and availability

The Telum chip is designed for environments where downtime is not an option, offering 99.999999% uptime for mission-critical systems. With built-in self-healing and redundancy mechanisms, it helps ensure continuous operation through automatic failover in the event of hardware or software failures. Also, real-time recovery capabilities allow the system to instantly reroute workloads, maintaining performance without interruption.

Optimized for hybrid cloud and multicloud

The Telum chip is cloud-native ready, designed for seamless operation with containerized applications and environments like Kubernetes and Red Hat® OpenShift®. It supports integration with public clouds such as AWS, Azure and IBM Cloud®, offering flexibility in deploying workloads across hybrid and multicloud settings. Also, its elastic scaling capabilities enable dynamic adjustment of workloads to handle demand fluctuations while helping ensure high performance.

High performance

The Telum chip features 8 cores with 16 threads per core, providing a total of 128 threads per processor for massive parallel processing of complex and high-demand workloads. With a clock speed of up to 5.5 GHz, it helps ensure fast execution of critical, data-heavy and time-sensitive tasks4. A large on-chip cache further enhances performance by improving data access speed and reducing latency, making it ideal for memory-intensive applications.

Energy efficiency

The Telum chip is designed with sustainability in mind, delivering high compute performance while minimizing energy consumption. Its energy-efficient design reduces both operational costs and environmental impact, helping organizations meet their sustainability goals without sacrificing performance.

Energy efficiency is further improved with Telum II with up to 15% core power reduction based on centralized IO and DPU design5.

Explore sustainability with IBM LinuxONE
Spyre Accelerator
PCIe card Spyre Accelerator Delivered via a 75W gen 5x PCIe-attached AI accelerator with 128 GB of LPDDR5 memory. IBM Spyre Accelerator is geared to handle larger, more complex AI use cases, including Generative AI and multimodal LLMs, with 32 (+2) cores, 2 MB scratchpad on each and >55% core utilization. Scalable by card and drawer, clients are able to take advantage of this efficient solution for next-generation AI challenges. Read the blog
Use cases Real-time fraud prevention

In industries where time is money, real-time fraud detection can save millions. The LinuxONE Telum chip processes transactions and runs AI models concurrently, catching fraud as it happens, without impacting performance. Financial institutions can now act in real-time with confidence.

Securing healthcare data

Healthcare organizations need more than performance—they need trust. With full encryption at every layer and built-in confidentiality features, the Telum chip helps ensure patient data is secure, even in hybrid cloud environments. Data is protected, enabling healthcare providers to innovate while maintaining regulatory compliance.

Advanced anti-money laundering

Advanced detection for suspicious financial activities, supporting compliance with regulatory requirements and mitigating the risk of financial crimes.

Take the next step

Discover IBM LinuxONE 4: Built with first-in-industry on-chip acceleration Telum processor, designed for real-time AI inferencing to help identify fraud.

Explore IBM LinuxONE 4
Footnotes

The IBM Telum II processor and the Spyre Accelerator are currently in tech preview.

2, 3, 4, 5 All projections for Telum II are based on pre-release hardware measurements and configurations.