Next Leap of AI Infrastructure is Here

Today’s advanced AI models are changing our lives rapidly. Accelerated compute infrastructure is evolving at unprecedented speed in all market segments. Flexible, robust, and massively-scalable infrastructure with next-generation GPUs is enabling a new chapter of AI.

In close partnership with NVIDIA, Supermicro delivers one of the broadest selections of NVIDIA-Certified systems providing the most performance and efficiency from small enterprises to massive, unified AI training clusters with the new NVIDIA H100 and H200 Tensor Core GPUs.

Together, we achieve up to nine times the training performance of the previous generation for some of the most challenging AI models, cutting a week of training time into just 20 hours. Supermicro systems with the H100 PCIe, HGX H100 GPUs, as well as the newly announced HGX H200 GPUs, bring PCIe 5.0 connectivity, fourth-generation NVLink and NVLink Network for scale-out, and the new NVIDIA ConnectX®-7 and BlueField®-3 cards empowering GPUDirect RDMA and Storage with NVIDIA Magnum IO and NVIDIA AI Enterprise software.

GPU System Portfolio
8U GPU System

8U Universal GPU System

Suited for Today’s Largest-Scale AI Training Models and HPC, Featuring Superior Thermal Capacity with Reduced Accoustics, More I/O, and Vast Storage

  • GPU: NVIDIA HGX H100 8-GPU and HGX H200 8-GPU
  • GPU Advantage: With 80 billion transistors, the H100 and H200 are the world’s most advanced chip ever built and delivers 5X faster training time than A100 for LLMs and up to 110X faster time results for HPC applications
  • GPU-GPU Interconnect: 4th Gen NVLink® at 900GB/s
  • CPU: Dual Processor, Intel or AMD
  • Memory: ECC DDR5 up to 4800MT/s
  • Drives: Up to 24 Hot-Swap NVMe U.2
4U Universal GPU System

4U Universal GPU System

Optimized for HPC and Advanced Enterprise AI Workloads and Use Cases. Modular by Design for Ultimate Flexibility

  • GPU: NVIDIA HGX H100 4-GPU or 8-GPU (liquid-cooled), and HGX H200 4-GPU or 8-GPU (liquid-cooled)
  • GPU Advantage : HGX H200 doubles LLM inference performance and speeds up LLM fine-tuning by 5.5X
  • GPU-GPU Interconnect: 4th Gen NVLink® at 900GB/s
  • CPU: Dual Processors
  • Memory: ECC DDR5 up to 4800MT/s
  • Drives: Up to 8 Hot-Swap NVMe U.2 connect to PCIe Switch or 10 Hot-Swap 2.5" SATA/SAS
4U 10-GPU System

4U or 5U 10GPU PCIe Gen 5 System

Flexible Design for AI and Graphically-Intensive Workloads, Supporting Up to 10 NVIDIA GPUs.

  • GPU: Up to 10 double-width PCIe GPUs
  • GPU Advantage: The NVIDIA L40S PCIe GPUs in this system are ideal for generative AI platform for high-quality images and immersive visual content
  • GPU-GPU Interconnect: Optional NVLink Bridge at 600GB/s
  • CPU: Dual Processors, Intel or AMD
  • Memory: ECC DDR5 up to 4800MT/s
  • Drives: 24 Hot-Swap Bays
  • Click here to register for 5 years of NVIDIA AI Enterprise Software included with each NVIDIA H100 PCIe GPU purchase
Tower/4U 4GPU System

4U 4GPU System

Optimized for 3D Metaverse Collaboration, Data Scientists, and Content Creators. Available in both Rackmount and Workstation Form Factors

  • GPU: Up to 4 double-width PCIe GPUs
  • GPU Advantage: NVIDIA L40S GPUs deliver up to 2x the real-time ray-tracing performance compared to the previous generation, making them ideal for creating beautifully-detailed, photorealistic models and scenes
  • GPU-GPU Interconnect: Optional NVLink Bridge at 600GB/s
  • CPU: Dual Processors, Intel or AMD
  • Memory: ECC DDR5 up to 4800MT/s
  • Drives: 8 Hot-Swap 3.5" drive bays, up to 8 NVMe drives, 2x M.2 (SATA or NVMe)
  • Click here to register for 5 years of NVIDIA AI Enterprise Software included with each NVIDIA H100 PCIe GPU purchase

Supermicro’s NVIDIA MGX™ Systems

2U NVIDIA MGX System with Intel- or ARM-based Processor

NVIDIA MGX Systems

Infinite Possibilities in a Modular Building Block Platform Supporting Today’s and Future GPUs, CPUs, and DPUs

  • GPU: Up to 4 NVIDIA double-width PCIe GPUs, including H100 PCIe, H100 NVL PCIe, L40S, and more
  • NVIDIA MGX Reference Design: Enabling to construct a wide array of platforms supporting both Arm®- and x86-based servers and is compatible with current and future generations of GPUs, CPUs, and DPUs
  • CPU: NVIDIA GH200 Grace Hopper™ Superchip, NVIDIA Grace™ CPU Superchip, or 4th Gen Intel® Xeon® Scalable processor
  • Memory: Up to 480GB integrated LPDDR5X DRAM (with Grace Hopper or Grace CPU Superchip) or up to 2TB 4800MT/s ECC DDR5 DRAM (with Intel CPU)
  • Drives: Up to 8 Hot-Swap E1.S NVMe
  • Networking: Supports NVIDIA BlueField®-3 DPU or NVIDIA ConnectX®-7

Test Drive Supermicro’s NVIDIA H100 System with Our Partners

Please register for the program by clicking one of our partner logos.

(Terms and Conditions apply. Please check the details with your preferred partner.)

Supermicro 4U NVIDIA H100 GPU system (front view)
4U 8-GPU NVIDIA OVX Reference Design System

2nd Gen NVIDIA OVX Reference Design Systems

New Purpose-Built Next Generation System Optimized to Power Immersive, Photorealistic 3D Models, Simulations, and Digital Twins

  • GPU: 8x NVIDIA L40S or L40
  • GPU Featureset: NVIDIA Ada Lovelace architecture with fastest 3rd generation ray tracing graphics (RT Cores) and 4th generation Tensor Cores
  • CPU: Dual Processor
  • Memory: ECC DDR5 up to 4800MT/s
  • Network: 3x ConnectX®-7 SmartNICs for 100G/200G networking

Supermicro Leads the Market with High-Performance A100 GPU Servers

Supermicro builds the most robust high-performance servers based on NVIDIA Ampere GPUs that have been used by leading enterprises leveraging large scale computer vision and natural language processing models. Supermicro supports a range of customer needs with optimized systems for the new HGX™ A100 8-GPU and HGX™ A100 4-GPU platforms. With the newest version of NVIDIA® NVLink™ and NVIDIA NVSwitch™ technologies, these servers can deliver up to 5 PetaFLOPS of AI performance in a single 4U system. Supermicro can also support NVIDIA’s Ampere GPU family in a range of PCIe systems, with up to 10 GPUs in a 4U server.

AS -2124GQ-NART photo

AS -2124GQ-NART

2U NVIDIA HGX A100 4-GPU
4x A100 40G/80G SXM4 GPUs
NVIDIA NVLink
Dual 3rd Gen AMD EPYC™ Processors
32 DIMM slots
2x 2200W Redundant Platinum Level PSU
Learn more
SYS-420GP-TNAR photo

SYS-420GP-TNAR

4U NVIDIA HGX A100 8-GPU
8x A100 40G/80GB SXM4 GPUs
NVIDIA NVLink and NVSwitch
Dual 3rd Gen Intel® Xeon® Scalable Processors
32 DIMM Slots
4x 2200W Redundant Platinum Level PSU
Learn more
AS -4124GO-NART photo

AS -4124GO-NART

4U NVIDIA HGX A100 8-GPU
8x A100 40G/80GB SXM4 GPUs
NVIDIA NVLink and NVSwitch
Dual 3rd Gen AMD EPYC™ Processors
32 DIMM Slots
4x 2200W Redundant Platinum Level PSU
Learn more
AS -2114GT-DNR Photo

AS -2114GT-DNR

2U 2-Node GPU Server
Up to 3 NVIDIA Ampere GPUs per Node
PCIe Gen 4
Single 3rd Gen AMD EPYC™ Processor per Node
8 DIMM Slots per Node
2x 2600W Redundant Titanium Level PSU
Learn more
SYS-420GP-TNR Photo

SYS-420GP-TNR

4U 10 GPU (PCIe)
Up to 10 NVIDIA Ampere GPUs
PCIe Gen 4
Dual 3rd Gen Intel® Xeon® Scalable Processors
32 DIMM slots
4x 2000W Redundant Titanium Level PSU
Learn more
AS -4124GS-TNR photo

AS -4124GS-TNR

4U 8 GPU (PCIe)
Up to 8 NVIDIA Ampere GPUs
PCIe Gen 4
Dual 3rd Gen AMD EPYC™ Processors
32 DIMM slots
4x 2000W Redundant Titanium Level PSU
Learn more

NVIDIA-Certified Systems™ by Supermicro

With the continued rollout of advanced applications and workloads, customers require manageable, secure, and scalable servers for their data centers. Supermicro's compelling lineup of high-performance servers supporting NVIDIA GPUs and DPUs includes a growing number of NVIDIA-Certified Systems, with many more currently undergoing the certification process. Each server/GPU configuration earns its own certification.

NVIDIA Certified Solutions logo

Learn More

Resources

Genesis Cloud Selects Supermicro's Powerful AI Servers For New Offerings

Genesis Cloud Offers AI and ML Services Using Supermicro Advanced AI Training System Featuring NVIDIA HGX H100 GPUs

View the success story

Supermicro Shows Liquid-Cooled NVIDIA H100 Delta Next at ISC 2023

By Patrick Kennedy -

Supermicro showed off a large number of systems at ISC 2023. One of them particularly will be impactful. Supermicro had a liquid-cooled 8x NVIDIA H100 Delta-Next platform at the show and it was different than we expected.

See the product review

Accelerated Compute Infrastructure for AI and HPC Workloads with Supermicro Solutions Featuring the NVIDIA® H100 GPU

Supermicro Infrastructure for Demanding AI/ML and HPC Environments

View the product brief

Supermicro TECHTalk: AI Training Powered by Supermicro 8U 8GPU Server & New NVIDIA H100 GPUs

Requirements for AI training and machine learning is growing exponentially. Supermicro provides the accelerated compute infrastructure for increasing the performance of AI training by 9 times over current products available.

Play the video

Supermicro TECHTalk: Media and Graphics powered by Supermicro 4U 10 GPU server

The new Supermicro servers that incorporate the NVIDIA L40 GPUs create the optimum system for driving AI media and graphics applications.

Play the video

Supermicro TECHTalk: High-Density AI Training/Deep Learning Server

Our newest data center system packs the highest density of advanced NVIDIA Ampere GPUs with fast GPU-GPU interconnect and 3rd Gen Intel® Xeon® Scalable processors. In this TECHTalk, we will show how we enable unparalleled AI performance in a 4U rack height package.

Play the video

Supermicro TECHTalk: The Lowest Latency, Highest Performance Peer-to-Peer GPU System in 2U

In the first episode of our new Supermicro Tech Talks series, we take a look at our 2U system featuring the NVIDIA HGX A100 4 GPU board with four direct-attached NVIDIA A100 Tensor Core GPUs using PCI-E 4.0 for maximum performance and NVIDIA NVLink™ for high-speed GPU-to-GPU interconnects.

Play the video

Supermicro TECHTalk: Large-Scale Data Center GPU Solution

In this episode of Supermicro TECHTalk, we reveal one of our newest systems, our A+ 2U 2-Node GPU Server, powered by 3rd Gen AMD EPYC processors. This system delivers unrivaled energy efficiency and flexibility for a new performance standard of video streaming, cloud gaming, and social networking applications.networking applications.

Play the video

SuperMinute: 4U System with HGX A100 8-GPU

For the most demanding AI workloads, Supermicro builds the highest-performance, fastest-to-market servers based on NVIDIA A100™ Tensor Core GPUs. With the newest version of NVIDIA® NVLink™ and NVIDIA NVSwitch™ technologies, these servers can deliver up to 5 PetaFLOPS of AI performance in a single 4U system.

Play the video

SuperMinute: 2U System with HGX A100 4-GPU

The new AS -2124GQ-NART server features the power of NVIDIA A100 Tensor Core GPUs and the HGX A100 4-GPU baseboard. The system supports PCI-E Gen 4 for fast CPU-GPU connection and high-speed networking expansion cards.

Play the video

Supermicro SuperMinute: 2U 2-Node Server

Supermicro's breakthrough multi-node GPU/CPU platform is unlike any existing product in the market. With our advanced Building Block Solutions® design and resource-saving architecture, this system leverages the most advanced CPU and GPU engines along with advanced high-density storage in a space-saving form factor, delivering unrivaled energy-efficiency and flexibility.

Play the video

Supermicro TECHTalk: 5 PetaFLOPS of AI Performance in a Single 4U Server

In this episode of Supermicro Tech Talks, we take a detailed look at our 4U System with HGX A100 8-GPU, ideal for large-scale deep learning training and neural network model applications.

Play the video

Delivering AI to Enterprises, with Supermicro Systems, NVIDIA AI Enterprise, and VMware

Supermicro Systems Supporting Scalable Virtualized AI Solutions

View the solution brief

Supermicro, Cloudera, & NVIDIA Accelerate Enterprise Data Analytics

How Supermicro Ultra Servers and Cloudera Data Platform Extract Deep Insights from Massive Amounts of Data

View the solution brief

Maximizing AI Development & Delivery with Virtualized NVIDIA A100 GPUs

Supermicro systems with NVIDIA HGX A100 offer a flexible set of solutions to support NVIDIA Virtual Compute Server (vCS) and NVIDIA A100 GPUs, enabling AI developments and delivery to run small and large AI models.

View the solution brief

Unleash the Future of Innovation with HPC & AI

Transforming businesses with a new class of Supermicro and NVIDIA high-performance solutions

View the solution brief

Deep Learning Benchmarks on Supermicro’s 4U 8 GPU System Based on Dual 3rd Gen AMD EPYC™ Processors

Demonstrating the performance of the Supermicro AS -4124GS-TNR, a 4U dual-processor 8 GPU server with up to 8TB of memory, and 160 Lanes of PCI-E 4.0, shows the generation over generation performance improvements of the new 3rd Gen AMD EPYC 7003 Series Processors on Deep Learning benchmarks

View the white paper

IDLab (Ghent University and the University of Antwerp) Implements Supermicro's Most Powerful Server, Cuts Down AI Research Experiment Time From Nearly Seven Hours Down To 40 Minutes

Supermicro’s new 10U GPU server using NVIDIA HGX-2 GPU baseboards helps leading Belgian research team improve calculation times by 10X which leads to faster AI development

View the success story

AI Workloads at Scale

Kubernetes Cluster with Supermicro’s Systems with AMD EPYC™ 7002 processors

View the white paper

Supermicro® System Combines AMD EPYC™ Processors and NVIDIA GPUs to Achieve Consistent Deep Learning Performance with Linear Scaling

Learn about the benchmark results for Supermicro AS - 2023US-TR4, an AMD EPYC™ CPU based Supermicro high-end enterprise GPU server platform.

View the white paper

Available Models

Card View List View
{"subgroup_0_1":["SYS-821GE-TNHR||5"],"subgroup_0_2":["SYS-821GV-TNR||14"],"subgroup_0_3":["AS -8125GS-TNHR||16"]}
8U Universal GPU Systems1
Loading Data
{"subgroup_1_1":["SYS-421GE-TNRT3||6","SYS-421GE-TNRT||1"],"subgroup_1_2":["SYS-521GE-TNRT||3"],"subgroup_1_4":["AS -4125GS-TNRT1||17","AS -4125GS-TNRT2||18","AS -4125GS-TNRT||15"]}
4U/5U GPU Lines with PCIe 5.02
Loading Data
{"subgroup_2_1":["SYS-421GU-TNXR||2"],"subgroup_2_2":["SYS-420GU-TNXR (IN 5U)||","SYS-420GU-TNXR (in 4U)||29"],"subgroup_2_4":["AS -4124GQ-TNMI (IN 5U)||","AS -4124GQ-TNMI (in 4U)||39"]}
4U/5U Universal GPU systems2
Loading Data
{"subgroup_3_1":["SYS-4029GP-TVRT||53"]}
4U GPU with NVLink2
Loading Data
{"subgroup_4_1":["SYS-221GE-NR||0"],"subgroup_4_2":["ARS-121L-DNR||8"],"subgroup_4_3":["ARS-221GL-NR||9"],"subgroup_4_4":["ARS-111GL-NHR||10"],"subgroup_4_5":["ARS-111GL-NHR-LCC||11"],"subgroup_4_6":["ARS-111GL-DNHR-LCC||12"]}
NVIDIA MGX™ Systems3
Loading Data
{"subgroup_5_1":["SYS-4029GP-TRT2||51","SYS-4029GP-TRT3||52","SYS-4029GP-TRT||41"],"subgroup_5_2":["SYS-6049GP-TRT||47"]}
4U GPU Lines3
Loading Data
{"subgroup_6_1":["SYS-420GP-TNR||19"],"subgroup_6_2":["AS -4124GS-TNR+||36","AS -4124GS-TNR||32"]}
4U GPU Lines with PCIe 4.04
Loading Data
{"subgroup_7_1":["SYS-420GP-TNAR+||26","SYS-420GP-TNAR+-US||28","SYS-420GP-TNAR||24"],"subgroup_7_4":["AS -4124GO-NART+||38","AS -4124GO-NART||35"]}
4U GPU with NVLink and PCIe 4.04
Loading Data
{"subgroup_8_1":["SYS-210GP-DNR||21"],"subgroup_8_2":["AS -2114GT-DPNR||33","AS -2114GT-DNR||31"]}
2U 2-Node Multi-GPU with PCIe 4.05
Loading Data
{"subgroup_9_1":["AS -2124GQ-NART-LCC||13"],"subgroup_9_2":["SYS-220GP-TNR||22"],"subgroup_9_3":["SYS-220GQ-TNAR+||25"],"subgroup_9_4":["AS -2124GQ-NART+||37","AS -2124GQ-NART||34"],"subgroup_9_6":["SYS-2029GP-TR||44"]}
2U GPU Lines6
Loading Data
{"subgroup_10_1":["SYS-120GQ-TNRT||23"],"subgroup_10_2":["SYS-1019GP-TT||42"],"subgroup_10_3":["SYS-1029GP-TR||43"],"subgroup_10_4":["SYS-5019GP-TT||45"],"subgroup_10_5":["SYS-1029GQ-TNRT||48","SYS-1029GQ-TRT||46"]}
1U GPU Lines7
Loading Data
{"subgroup_11_1":["SYS-741GE-TNRT||4"],"subgroup_11_2":["SYS-751GE-TNRT-NV1||7"],"subgroup_11_3":["SYS-740GP-TNRBT||27","SYS-740GP-TNRT||20"]}
GPU Workstation8
Loading Data
{"subgroup_12_1":["SYS-1029GQ-TXRT||50","SYS-1029GQ-TVRT||49"]}
1U GPU with NVLink11
Loading Data
{"subgroup_13_1":["SYS-9029GP-TNVRT||54"]}
10U 16-GPU with NVLink13
Loading Data
System List
Product GroupHiddenOrderSKUDescriptionLinkImageGenerationComingNewGlobalGPUGPU-GPUCPUCPU TypeDIMM SlotsDrive SizeDrivesNetworkingForm FactorTotal PCI-E Slots#Total PowerGPU TypeInterfaceRedundant PowerApplications