AMD launches Instinct MI400 Series GPUs combining HBM4 memory, 40 PFLOPs AI compute, and Helios system-level optimization.

On July 23, 2026, at Advancing AI 2026, AMD launched the AMD Instinct MI400 Series GPUs, the next generation of data center accelerators engineered to redefine artificial intelligence and high-performance computing (HPC) at every scale. The lineup features the AMD Instinct MI455X GPUs, designed for frontier AI and AI factory deployments, and the AMD Instinct MI430X GPU, tailored for sovereign AI and HPC. By combining leadership compute and networking performance, high-bandwidth HBM4 memory, advanced security features, and scalable system architectures, the MI400 series enables organizations to deploy, scale, and manage AI and HPC workloads with greater flexibility and confidence.

AI infrastructure is growing increasingly specialized as organizations deploy models across diverse environments. These range from hyperscale AI factories focused on large-scale inference and frontier-model training to sovereign AI and scientific computing centers that require strict numerical accuracy, robust security, and long-term operational control. The AMD Instinct MI400 series addresses both paradigms with purpose-built solutions, allowing customers to deploy optimized infrastructure while preserving the openness, interoperability, and software portability necessary to scale future workloads.

“The next generation of AI will span frontier AI, sovereign AI and scientific computing, and each requires infrastructure optimized for its unique demands,” said Vamsi Boppana, senior vice president, AI, AMD. “The AMD Instinct MI400 Series extends our AI portfolio with purpose-built solutions optimized for the full spectrum of AI and HPC deployments, built on an open software foundation that gives customers the flexibility to innovate at every scale.”

The AMD Instinct MI400 Series integrates purpose-built hardware, an open software ecosystem, and scalable system design to meet the evolving demands of modern AI and HPC deployments. Key capabilities include:

**Purpose-Built AI Infrastructure:** The portfolio spans the AMD Helios rackscale solution, powered by MI455X GPUs for frontier AI and AI factory workloads, alongside MI430X GPUs for sovereign AI and HPC. Together, they deliver optimized solutions for hyperscale AI factories, national research infrastructure, academic institutions, and leadership-class HPC environments.

**Leadership Performance Across AI and HPC:** The MI455X GPUs provide the compute, memory, and networking throughput required for high-volume inference, frontier-model training, and fine-tuning. Meanwhile, the MI430X GPUs deliver uncompromised accuracy and throughput across converged AI and HPC workflows, featuring up to 288 TFLOPS of hardware-based FP64 performance for scientific computing. Across the entire series, industry-leading HBM4 memory and high memory bandwidth enable customers to support larger models, reduce infrastructure complexity, and improve operational efficiency at scale.

**Open Software Foundation:** Built on the AMD ROCm software platform, the MI400 Series offers a comprehensive open-source foundation, including programming models, compilers, libraries, runtimes, and deployment tools. This commitment to open standards ensures interoperability and long-term portability across software, system, and networking stacks, allowing customers to innovate without vendor lock-in.

**Secure and Scalable by Design:** The GPUs incorporate advanced security features, including secure boot, encrypted GPU-to-GPU links, and hardware-level protections to safeguard sensitive AI and HPC workloads. Paired with flexible system architectures—ranging from the AMD Helios rackscale solution for frontier AI to traditional mesh-based HPC deployments—the MI400 series empowers organizations to build AI infrastructure that balances flexibility, security, and long-term operational consistency.

AMD (NASDAQ: AMD) drives innovation in high-performance and AI computing to address the world’s most critical challenges. Today, AMD technology powers billions of experiences across cloud and AI infrastructure, embedded systems, AI PCs, and gaming. Backed by a comprehensive portfolio of AI-optimized CPUs, GPUs, networking solutions, and software, AMD delivers full-stack AI platforms that provide the performance and scalability required for a new era of intelligent computing. For more information, visit www.amd.com.