- Supermicro launches highly optimized AI solutions, based on AMD Instinct MI350 Series and AMD ROCM ™ software, offering inference performance and electrical efficiency.
- The new H14 Supermicro GPU solutions are fueled by the most recent 4th AMD CDNA ™ Architecture generation, offering optimized performance and efficiency for large AI training models and high -speed workloads
- Large memory capacity with 2.304 TO HBM3E Total per 8-GPU server which offers faster calculation and more efficient scaling for AI, inference and training
San Jose, California.,, June 13, 2025 / Prnewswire / – SupermicroInc. (NASDAQ: SMCI), a total supplier of IT solutions for AI, Cloud, Storage and 5G / EDGE, announces that GPU solutions cooled and cooled by air will be available with the new GPUs in the MI350 AMD MI350 series, optimized for unrivaled performance, maximum scalability and efficiency. The H14 SuperMicro H14 generation of GPU optimized solutions with Dual AMD EPYC ™ 9005 processors as well as GPUs in the AMD Instinct MI350 series, are designed for organizations that are looking for maximum -scale performance, while reducing the total property cost for their data centers induced by AI.
“Supermicro continues to direct the industry with the most experience in the provision of high performance systems designed for AI and HPC applications,” said Charles LiangPresident and chief executive officer of Supermicro. “Our solutions for building the data center® Allow us to quickly deploy data center solutions from start to finish on the market, bringing the latest technologies for the most demanding applications. The addition of the new GPUs of the MI350 AMD MI350 MI350 series to our range of GPU servers strengthens and extends our AI solutions to the head of the industry and gives customers a greater choice and better performance during the design and construction of the next generation of data centers. “”
Find out more about supermicro servers with AMD Instinct MI350 Series Gpus here.
Supermicro H14 generation H14 data center solutions offer unrivaled performance and flexibility for a wide range of AI, HPC, Cloud and business workloads. These systems are built on the proven architecture of Building-Block of Supermicro to help business customers effectively put their workloads and effectively evolve. The new GPU Supermicro servers present both the latest AMD EPYC CPUS and AMD Instinct GPUs which offer together a powerful family of solutions compatible with AI, adding to the solutions of construction center of the Supermicro data center, ensuring the success of the customer of the consultation to the deployment and support on site.
“Our new AMD Instinct MI350 series offers up to 40% tokens per dollar compared to competition, while retaining the standard formal factor in industry for OEM infrastructure compatibility,” said Dr. Lisa isCEO and President, AMD. “By combining these GPUs with proven supermicro platforms, their customers can deploy fully integrated racks, air or liquid cooled, fully built on AMD technology, which gives them flexibility and efficiency they need to deploy robust AI solutions to any scale.”
SuperMicro is expanding its high-performance liquid and air cooled cooling and air-cooled cooling fabric system, taking advantage of the standard OCP OCP accelerator module from the Open multi-architecture industry (OAM) to support the latest GPUs in the MI350 AMD Instinct MI350 series. For higher density environments, the 4u liquid system with AMD Instinct MI355X offers a new Direct Liquid Cooling Architecture (DLC) of Supermicro incorporating new technologies to cool various server components and reducing energy consumption up to 40%, unlocking higher performance by Rack and supporting the advanced cooling infrastructure. Customers can choose the 4u Supermicro liquid cooling 4u option for upper rack deployments as well as the 8U option for air -cooled environments.
Designed to maximize the calculation flow, the use of the bandwidth of memory and energy efficiency to allow an IA more efficient IA inference. These accelerated GPU servers with the AMD Instinct MI350 series will offer 288 GB of HBM3E per GPU, increasing the memory capacity by 1.5x compared to previous generations of AMD instinct, 8TB / S bandwidth and 1.8x Petaflops of FP16 / FP8 compared to the load of previous generation MI325X, so that customers Data to do more data on AI.
“The AI models do not increase simply in size; they require a faster and more efficient infrastructure which can remain constantly deployable in real environments,” said Paul SchellIndustry analyst at Abi Research. “By adding GPUs of the AMD MI350 series in its latest generation H14, Supermicro demonstrates a commitment to provide evolutionary, high performance and memory solutions that are optimized for both the formation and efficiency of AI. With support for liquid and air cooling, these systems offer flexibility and efficiency that CSPS, neo-clud and undertakes.
These new GPU solutions are designed to supply large -scale AI, between cloud service providers and corporate partners, built on the 4th generation AMD ARDN Architecture, the AMD Instinct MI350 series offers exceptional energy performance and efficiency for a wide range of workloads, training and IA inference to complex scientific simulations. The new AMD MI350 series will also include new FP6 and FP4 data types to provide exceptional AI capabilities, managing larger models for AI deployments.
These Supermicro GPU systems with AMD Instinct GPUs are available on order:
GPU cooled by liquid, 4u https://www.supermicro.com/en/products/system/gpu/4u/as%20-4126gs-nmr-lcc
GPU cooled by Air, 8u
https://www.supermicro.com/en/products/system/gpu/8u/as%20-8126gs-tnmr
About Super Micro Computer, Inc.
Supermicro (NASDAQ: SMCI) is a world leader in total IT solutions optimized by the application. Founded and operating in San Jose, CaliforniaSuperMicro undertakes to first deliver to market innovation for the IT infrastructure of the company, the cloud, the AI and the 5G. We are a total manufacturer of computer solutions with server, AI, storage, IoT, switching systems, software and support services. The design of the design of the motherboard, energy and supermicro chassis also allows our development and production, allowing new generation of the cut -off generation for our global customers. Our products are designed and manufactured internally (in the United States, AsiaAnd The Netherlands), Take advantage of global operations for scale and efficiency and optimized to improve TCO and reduce the environmental impact (Green IT). The award -winning portfolio of Building Block Solutions® servers allows customers to optimize their accurate workload and application by selecting from a wide family of systems built from our flexible and reusable construction blocks that support a full set of formal factors, processors, memory, GPU, storage, networking, electricity and cooling (Cooling in the open air or cash cooling).
Supermicro, Server Building Block Solutions, and we keep it green are commercial brands and / or registered trademarks of Super Micro Computer, Inc.
All other brands, names and brands are the property of their respective owners.
Super micro Computer source, Inc.
