SAN JOSE, CA, June 17, 2025 – Supermicro has introduced both liquid-cooled and air-cooled GPU solutions using the AMD Instinct MI350 series. Their H14 generation systems combine dual AMD EPYC 9005 processors with these GPUs. This setup targets organizations that require high-performance computing at scale, aiming to balance performance needs with cost efficiency in AI-focused data center environments.
“Supermicro continues to lead the industry with the most experience in delivering high-performance systems designed for AI and HPC applications,” said Charles Liang, president and CEO of Supermicro. “Our Data Center Building Block Solutions enable us to quickly deploy end-to-end data center solutions to market, bringing the latest technologies for the most demanding applications. The addition of the new AMD Instinct MI350 series GPUs to our GPU server lineup strengthens and expands our industry-leading AI solutions and gives customers greater choice and better performance as they design and build the next generation of data centers.”
Supermicro’s H14 data center systems support a range of AI, HPC, Cloud, and Enterprise needs. These platforms use Supermicro’s building-block design, which helps companies upgrade and scale their workloads. The new Supermicro GPU servers combine the AMD EPYC CPU and AMD Instinct GPUs. This combination provides a strong option for organizations running AI workloads. These products fit into Supermicro’s data center building block solutions (DCBBS) to support customers from planning through to on-site deployment and support.
“Our new AMD Instinct MI350 series delivers up to 40 percent more tokens-per-dollar relative to the competition, while retaining the industry standard form factor for OEM infrastructure compatibility,” said Dr. Lisa Su, CEO and Chair, AMD. “By combining these GPUs with Supermicro’s proven platforms, their customers can deploy fully integrated, air- or liquid-cooled racks built entirely on AMD technology, giving them the flexibility and efficiency they need to deploy robust AI solutions at any scale.”
Supermicro is expanding its line of liquid-cooled and air-cooled 8-GPU systems based on the open OCP Accelerator Module (OAM) module to work with AMD Instinct MI350 series GPUs. For dense environments, the 4U liquid-cooled system with AMD Instinct MI355X GPUs uses an updated Direct Liquid Cooling (DLC) system. This system uses new cooling technologies for different server parts and can help reduce power use by up to 40 percent. The system supports performance per rack and is compatible with large-scale cooling setups. Customers can choose a 4U liquid-cooled design for dense data centers or an 8U air-cooled option for less dense environments.
These GPU servers, built with AMD Instinct MI350 series chips, focus on higher computing power, memory use, and energy savings. Each GPU includes 288GB of HBM3e memory, increasing its capacity by 1.5 times compared to earlier AMD Instinct models. Bandwidth reaches 8TB per second. Performance for FP16 and FP8 is also up 1.8 times over the previous Instinct MI325X. This allows users to handle larger datasets and speed up AI tasks.
“AI models aren’t just increasing in size; they’re demanding faster, more efficient infrastructure that can stay consistently deployable in real-world environments,” said Paul Schell, Industry Analyst at ABI Research. “By adding AMD MI350 series GPUs into its latest H14 generation, Supermicro demonstrates a commitment to providing scalable, high-performance and memory solutions that are optimized for both AI training and inference. With support for both liquid and air cooling, these systems offer the flexibility and efficiency that CSPs, neo-clouds and enterprises alike need to power the next wave of AI growth.”
The new GPU solutions support AI projects for both cloud services and business partners. Built on AMD’s fourth-generation CDNA architecture, the Instinct MI350 Series focuses on strong performance and energy savings for tasks like AI training, inference and scientific modeling. The MI350 Series also adds FP6 and FP4 data types, making it easier to work with larger AI models.
Source: Super Micro
About Super Micro
Super Micro Computer Inc., or Supermicro, is a provider of high-performance server technology and green computing solutions. Founded in 1993 by Charles Liang and Sara Liu, the company is headquartered in San Jose, CA. Supermicro offers a complete range of products, including servers, storage systems, networking devices, and server management software, serving industries like enterprise data centers, cloud computing, artificial intelligence, 5G, and edge computing. As of June 2023, the company employs approximately 5,126 individuals globally. In the fiscal year 2024, Supermicro reported revenues of approximately $15 billion, reflecting growth driven by its innovative solutions and expanding market presence.