GPU Server Solutions AI/ML Servers

Unlock the full potential of your AI, machine learning, and high-performance computing workloads with GPU servers from Dell EMC, Supermicro, and HPE ProLiant. Purpose-built for demanding data analytics, deep learning, and HPC environments, these enterprise-grade systems deliver exceptional processing power, memory bandwidth, and scalability. Whether you're training large language models, running real-time inference, or managing complex data pipelines, serverandparts.com has the configuration to match your workload and budget. Browse our full selection of in-stock GPU servers and find the performance your business needs — without the wait.

Shop Now

Filters

Price Range

Min ($)

Max ($)

$0$10,000+

Subcategory

Supermicro GPU Servers

HPE GPU Servers

Dell EMC GPU servers

Brand

HPE

SuperMicro

Memory11

16 DIMM slots (16 DIMM channels per processor), up to 2TB total DDR5, speeds up to 5600 MT/s; only HPE DDR5 5600 MT/s SKUs can be selected with 5th Generation Intel processors; registered ECC DDR5 only124 DDR5 DIMM slots, 12 DIMM channels per processor, up to 3TB total, speeds up to 5600 MT/s; HPE DDR5 Smart Memory124 DDR5 RDIMM slots, max capacity 3TB132 DDR5 DIMM slots, RDIMM 8TB max; speeds up to 4800 MT/s (4th Gen Xeon) or 5600 MT/s (5th Gen Xeon); registered ECC DDR5 DIMMs only132 DDR5 DIMM slots, up to 3TB total, speeds up to 6400 MT/s1

Networking2

2x 1GbE LOM embedded; OCP 3.0 Mezz x8 card options (Intel 10GbE x4, Broadcom 25GbE x2)2Supports the latest NVIDIA InfiniBand, Ethernet and BlueField adapters, including NDR/NDR200 InfiniBand and BlueField DPU options; NVIDIA OVX certified1

Form Factor9

Accelerators — AMD1

8x AMD Instinct MI300X 192GB 750W OAM accelerator with AMD Infinity Fabric connectivity1

Accelerators — Intel1

8x Intel Gaudi3 128GB 900W OAM accelerator with embedded RoCE ports for Ethernet connectivity1

Accelerators — NVIDIA1

8x NVIDIA HGX H100 80GB 700W SXM5 GPUs, or 8x NVIDIA HGX H200 141GB 700W SXM5 GPUs, both fully interconnected via NVIDIA NVLink1

More technical filters107

Acoustics1

LWA,m 9.5 B; LpAm 80 dBA (tested in performance configuration at 100% CPU and GPU TDP)1

Acoustics — B200 Config1

Idle: LwA,m 7.2B, LpA,m 60dBA; Operating: LwA,m 7.8B, LpA,m 64dBA @25°C ambient; scales to 8.8B/71dBA @35°C ambient2

Acoustics — H200 Config1

Idle: LwA,m 7.4B, LpA,m 61dBA; Operating: LwA,m 7.6B, LpA,m 62dBA @25°C ambient; scales to 8.2B/68dBA @35°C ambient2

Air Filter1

Bezel filter kit with removable air filter; HPE recommends replacement every three to six months (consumable, not covered under warranty)1

Available Color1

Black Front & Silver Body4

BIOS1

AMI 64MB SPI Flash EEPROM4

Bezel2

Optional LCD bezel or security bezel4Optional security bezel1

CPU Cores1

72 Arm Neoverse V2 cores (GH200) or 144 Arm Neoverse V2 cores (GH200 NVL2); base frequency 3.1GHz, all-core SIMD frequency 3.0GHz1

CPU-GPU Interconnect2

Direct Attached3PCIe 5.0 x16 Switch Dual-Root1

Cache1

64KB i-cache + 64KB d-cache L1; 1MB L2 per core; 114MB L3 (GH200) or 228MB L3 (GH200 NVL2)1

Change Management1

Enterprise Catalogs / Linux Repositories1

Chassis2

10DW (double-wide GPU) chassis with one drive bay for drive cage options; ships with one 4SFF x4 U.3 NVMe drive cage by default14DW (double-wide GPU) chassis with one drive bay for drive cage options; ships with an 8SFF x4 U.3 NVMe drive bay by default1

Chassis Dimensions1

Height 174.3mm (6.86"), Width Upper 2U 447mm (17.59")/Lower 2U 434mm (17.08"), Depth with bezel 1037.57mm (40.82")/without bezel 1025.62mm (40.37")2

Chipset1

Intel C741 chipset3

Compute Performance (GH200 NVL2)1

FP64 68 teraFLOPS; FP64 Tensor Core 134 teraFLOPS; FP32 Tensor Core up to 1979 teraFLOPS; BFLOAT16 Tensor Core up to 3958 teraFLOPS with sparsity; FP8 Tensor Core up to 7916 teraFLOPS with sparsity; INT8 Tensor Core up to 7916 TOPS with sparsity1

Cooling11

Up to 10 heavy duty fans with optimal fan speed control4Air cooled1Air cooled, front to back; 52 CFM idle entry, 133 CFM idle typical with DPU, 240 CFM operating maximum at 25C ambient1Air cooled, with a thermal design tuned for dense GPU configurations1Air cooling1

Cooling and Environment1

Continuous operation from -5C to 55C; withstands high-dust and high-vibration environments; designed to qualify for NEBS Level 31

Dimensions7

Height 8.75" (222.5mm), Width 17.2" (438mm), Depth 31" (786.1mm)4Approximately 15 inches wide; 16 inches deep without bezel, 20 inches deep with bezel filter1Height 10.36" (263.20mm), Width 18.97" (482.00mm), Depth with bezel 39.71" (1008.77mm)/without bezel 39.17" (995.00mm)1Height 3.41" (86.8mm), Width 18.97" (482mm), Depth 37.27" (946.73mm) without bezel/36.73" (932.89mm) with bezel1Height 6.86" (174.3mm), Width 18.97" (481.91mm), Depth with bezel 35.48" (901.4mm)/without bezel 34.07" (865.54mm)1

Drive Bays8

8 SFF (SAS/SATA/NVMe) with optional Universal Media Bay; 4 LFF with optional optical disk drive and DisplayPort/USB kit; 8 EDSFF x4 NVMe drive cage option18x 2.5" NVMe/SAS/SATA SSDs (122.88TB max)18x 2.5" NVMe/SAS/SATA SSDs (122.88TB max), or 16x E3.S NVMe SSDs (122.88TB max)18x U.2 NVMe SSD drives, direct-attached from PSB (front bays)1Total 10 bays: 2 front hot-swap 2.5" SATA + 8 front fixed 2.5" NVMe drive bays1

Drive Bays — Default1

Total 6 bays: 2 front hot-swap 2.5" SATA + 4 front hot-swap 2.5" NVMe3

Drive Bays — Front1

Up to 6x E3.S Gen5 NVMe (46.08TB max); up to 6x 2.5" NVMe (92.16TB max); up to 8x 2.5" SAS/SATA/NVMe (122.88TB max)1

Drive Bays — Option A1

Total 2 bays: 2 front hot-swap 2.5" SATA3

Embedded Management10

iDRAC9, iDRAC Direct, iDRAC RESTful API with Redfish, iDRAC Service Module2HPE iLO 6 ASIC, iLO RESTful API with Redfish, UEFI Class 3 (UEFI boot mode only, no legacy mode), HPE Active Health System, RESTful Interface Tool (iLOREST)1HPE iLO 6 with Intelligent Provisioning; HPE Compute Ops Management1HPE iLO 6; HPE Compute Ops Management1HPE iLO 6; HPE Compute Ops Management; HPE OneView1

Embedded NIC4

2x 1GbE12x 1GbE LOM card (optional)1Broadcom BCM5720 Ethernet 1Gb 2-port BASE-T Adapter standard, upgradeable with a range of networking options1NA1

Embedded OSFP1

6x 800Gb (available only with Intel Gaudi3)1

Environmental — ASHRAE A2 Only1

10-35°C (50-95°F) at ≤900m altitude, 8-80% RH non-condensing, 1°C/300m de-rating above 900m; ASHRAE A3/A4 environments NOT supported for this platform2

Expansion1

PCIe Gen51

Expansion Slots1

Up to 12 PCIe Gen5 x16 slots (Full-height, Half-length): 10 general-purpose + 2 dedicated for NIC/SmartNIC/DPU (slots 33, 39); DPUs >75W must use slots 33/392

Fans6

4 hot-plug fan assemblies, each consisting of one dual-rotor 92x56mm fan and two single-rotor 40x28mm fans; a 110W fan upgrade is recommended to cool higher-temperature 600W GPUs14 standard or high-performance hot-plug fans, rear-mounted, drawing air through the front filter bezel16 dual-rotor hot-plug fans with N+1 redundancy by default16x Standard (STD) fans in mid tray + 5x high-performance (HPR) gold grade fans on the front; all hot-swap1Standard (STD) fans, up to six hot-plug1

Field Upgrades1

No field upgrade kits. HPE does not support changes to the number of superchips, drives, PCIe or OCP slots outside the factory1

Form Factor & Dimensions1

4U rack server — height 174.3mm (6.86in), width 482mm (18.98in), depth 899.56mm with bezel / 886.73mm without bezel1

Front Bays1

Up to 8x 2.5" NVMe/SAS/SATA SSD drives (max 122.88TB), or up to 16x E3.S NVMe direct drives (max 122.88TB); only 8x 2.5" NVMe supported with Intel Gaudi31

GPU1

4x NVIDIA HGX H100 SXM5 GPUs, fully interconnected with NVIDIA NVLink technology; up to 900GB/s GPU-to-GPU bandwidth; NVIDIA Multi-Instance GPU (MIG) supported1

GPU / Accelerators1

Up to 8x PCIe Gen5 double-wide GPUs (600W each) or 16x PCIe Gen5 single-wide GPUs (75W each)1

GPU Capacity1

8x PCIe Gen5 x16 DW-FHFL up to 600W, or 16x PCIe Gen5 x16 SW-FHFL up to 75W1

GPU Interconnect1

NVIDIA 2-way NVLink Bridge supported between two adjacent GPUs to increase inference performance1

GPU Options3

8x NVIDIA HGX H200 141GB 700W SXM5 GPUs (NVLink interconnected), or 8x NVIDIA HGX B200 180GB 1000W SXM6 GPUs (NVLink interconnected)2NVIDIA RTX PRO 6000 Blackwell Server Edition 600W (DW, 96GB); NVIDIA H200 NVL 600W (DW, 141GB); NVIDIA H100 NVL 400W (DW, 94GB); NVIDIA L40S 350W (DW, 48GB); NVIDIA L4 72W (SW, 24GB)1Up to 4x 400W double-width PCIe x16 GPU cards, or up to 12x 75W single-width PCIe x8 GPU cards; supports PCIe GPU adapters from NVIDIA, AMD and Intel1

GPU Support6

Up to 8 double-width GPUs, NVIDIA Certified; Supported: NVIDIA PCIe H100 NVL, H200 NVL (141GB), L40S, RTX PRO 6000 Blackwell Server Edition; AMD PCIe Instinct MI350P3Up to 10 double-wide GPUs at up to 600W each, or up to 16 single-wide GPUs1Up to 10 double-width GPUs, NVIDIA Certified; Supported: NVIDIA PCIe H100 NVL, H200 NVL (141GB), L40S, RTX PRO 6000 Blackwell Server Edition; AMD PCIe Instinct MI350P1Up to 3 single-wide GPUs, or 1 double-wide GPU1Up to 4 double-wide or 8 single-wide GPUs. Note: 0-GPU configurations are not allowed, and GPU installation after shipment must be performed by HPE Services1

GPU-GPU Interconnect2

NVIDIA NVLink Bridge (optional), AMD Infinity Fabric Link (optional)3NVIDIA NVLink Bridge (optional)1

High-Bandwidth Memory1

144GB HBM3e up to 4.9TB/s (GH200) or 288GB HBM3e up to 9.8TB/s (GH200 NVL2)1

Hot-Swappable Fans1

4 sets HPR in mid tray + 12 HPR on the front1

Internal Boot5

BOSS-N1 (HWRAID 1, 2x M.2 NVMe SSDs)1BOSS-N1 (HWRAID 1, 2x M.2 NVMe SSDs); Software RAID: S1601HPE NS204i-u Gen11 NVMe hot-plug Boot Optimized Storage Device1Hot-pluggable or internal high-availability RAID1 NVMe M.2 boot options1Up to two M.2 devices (PCIe Gen3); recommended for boot rather than local cache. Boot options set in HPE iLO from M.2 NVMe, EDSFF NVMe, or network PXE1

LAN1

1x RJ45 1GbE Dedicated BMC LAN port, 2x RJ45 10GBASE-T LAN ports4

LPDDR5X Memory1

480GB at 512GB/s (GH200) or 960GB at 1024GB/s (GH200 NVL2)1

M.21

1x M.2 PCIe 3.0 x4 NVMe slot (M-key)4

Management & Security1

iDRAC10, iDRAC Direct, RESTful API (Redfish), RACADM CLI; Secure Boot, signed firmware, Secured Component Verification, Silicon Root of Trust, TPM 2.01

Management Consoles1

CloudIQ for PowerEdge plugin, OpenManage Enterprise, OpenManage Power Manager plugin, OpenManage Service plugin, OpenManage Update Manager plugin1

Management Software1

SuperCloud Composer (SCC), Supermicro Server Manager (SSM), Supermicro Update Manager (SUM), Super Diagnostics Offline (SDO), Supermicro Thin-Agent Service (TAS), SuperServer Automation Assistant (SAA)4

Management Tools1

Dell System Update, Dell Repository Manager, Enterprise Catalogs, iDRAC RESTful API with Redfish, IPMI, RACADM CLI1

Max Memory (1DPC)1

Up to 6TB 6400MT/s ECC DDR5 RDIMM (EPYC 9005) or 4800MT/s (EPYC 9004)4

Maximum Heat Dissipation1

3048 Watts (10.4k BTU/hr) for a fully populated GH200 NVL2 system1

Maximum Weight2

135.36lb (61.4kg)1151.02lb (68.5kg)1

Maximum Weight (fully populated)1

Single superchip 26kg (58lb); dual superchip 31kg (69lb)1

Memory Population2

DIMMs must be selected in quantities of 1, 2, 4, 6, 8, 12 or 16; DIMM blanks required in each empty slot1Intel Xeon 6700-Series with E-cores limits DIMM quantities per CPU to 1, 2, 4, 8 and 16; 6500/6700-Series with P-cores allows 1, 2, 4, 8, 12 and 161

Memory Slots1

24 DIMM slots4

Memory Voltage1

1.1V4

Mobility1

OpenManage Mobile1

Mounting1

Wall, desk and rack mounting options; ruggedised option kit available1

NVIDIA NVLink-C2C CPU-to-GPU Bandwidth1

900GB/s (GH200) or 1800GB/s (GH200 NVL2)1

Network Connectivity1

2x RJ45 10GbE4

Network Options5

1x OCP 3.0 (optional), 2x 1GbE LOM (optional)11x OCP 3.0 (x8 PCIe lanes)11x OCP NIC card 3.0 (x8 PCIe lanes)11x OCP card 3.0 (optional). Note: the system allows either a LOM card, an OCP card, or both to be installed1Choice of OCP or stand-up card, supporting a range of NIC adapters1

Non-Operational Limits1

Temperature -40 to 65°C (-104 to 149°F); Humidity 5-95% RH, 27°C max dew point; Max altitude 12,000m (39,370ft) storage, 3,050m (10,006ft) operational2

OEM Availability1

OEM-ready version available — bezel to BIOS to packaging customization1

On-Board Devices1

SATA (6Gbps)4

OpenManage Console1

OpenManage Enterprise (OME), OME Power Manager, OME Services, OME Update Manager, OME APEX AIOps Observability, OME Integration for VMware vCenter (with VMware Aria Operations)1

OpenManage Integrations5

BMC TrueSight, Microsoft System Center, OpenManage Integration with ServiceNow, Red Hat Ansible Modules, Terraform Providers, VMware vCenter and vRealize Operations Manager1BMC TrueSight, OpenManage Integration with ServiceNow1BMC TrueSight, OpenManage Integration with ServiceNow, Red Hat Ansible Modules, Terraform Providers1BMC TrueSight, ServiceNow, Red Hat Ansible Modules, Terraform Providers1Red Hat Ansible Modules, Terraform Providers1

OpenManage Software2

CloudIQ for PowerEdge plugin, OpenManage Enterprise, OpenManage Service plugin, OpenManage Power Manager plugin, OpenManage Update Manager plugin2OpenManage Enterprise, OpenManage Power Manager plugin, OpenManage Service plugin, OpenManage Update Manager plugin, CloudIQ for PowerEdge plugin, OpenManage Enterprise Integration for VMware vCenter, OpenManage Integration for Microsoft System Center, OpenManage Integration with Windows Admin Center1

Operating Environment1

Operating Temp 10-35°C (50-95°F); Non-operating -40-60°C (-40-140°F); Operating Humidity 8-90% non-condensing; Non-operating Humidity 5-95% non-condensing4

Operating Temperature1

10C to 35C (50F to 95F) at sea level, with altitude derating of 1.0C per 305m above sea level to a maximum of 3050m; extended ambient ranges supported on approved hardware configurations1

PC Health Monitoring1

7+1 phase-switching voltage regulator; CPU cores/chipset voltages/memory monitoring; PWM fan tachometer and speed control; thermal control4

PCIe Slots8

4x x16 Gen516 PCIe Gen5 expansion slots; refer to HPE QuickSpecs for slot configuration rules1Up to 10x x16 Gen5 (x16 PCIe) full-height, half-length (8 slots with Intel Gaudi3)1Up to 2x x16 PCIe Gen5 slots plus 1x OCP 3.0 slot1Up to 4 full-height half-length x16 Gen5 PCIe slots, or 2 PCIe plus 2 OCP 3.0 x16 slots, depending on factory configuration1

PSU Input1

2700W: 200-240Vac / 50-60Hz; 2700W: 240Vdc / 50-60Hz (CQC only)4

PSU Ratings1

2800W: 10,500 BTU/hr, 200-240VAC, 15.6A, 96% Titanium efficiency; 3000W: 10,900 BTU/hr, 209.1-240VAC, 16A, 96% Titanium efficiency2

Package Dimensions1

17.32" (H) x 28.34" (W) x 42.51" (D)4

Ports — Front5

1x USB 2.0, 1x iDRAC Direct (Micro-AB USB), 1x VGA21x iDRAC Direct (Micro-AB USB) port, 1x USB 2.0, 1x VGA21x USB 2.0 Type-A (optional), 1x Mini-DisplayPort (optional), 1x USB 2.0 Type-C dual mode (Host/iDRAC Direct port)11x iDRAC Direct (Micro-AB USB), 1x USB 2.0, 1x VGA11x iLO Service Port, 1x USB 3.2, front panel LEDs for Unit ID, NIC status, health and power1

Ports — Internal2

1x USB 3.0 (optional)11x USB 3.1 Type-A1

Ports — Rear5

1x USB 2.0, 1x USB 3.0, 1x VGA, 1x RJ45 iDRAC9 Ethernet port21x USB 2.0, 1x iDRAC Direct Ethernet port, 1x USB 3.0, 1x dedicated iDRAC9 Ethernet port21x dedicated iDRAC Ethernet port, 1x USB 2.0, 1x USB 3.0, 1x Serial (optional), 1x VGA (optional for Direct Liquid Cooling configuration)11x dedicated iDRAC/BMC Direct Ethernet port, 2x USB 3.1 Type-A port, 1x VGA12x USB 3.0, 1x 1Gb iLO dedicated NIC, 1x serial, 1x VGA, 1x rear Unit ID indicator1

Power1

Three independent power domains, two of which are dedicated to the GPUs, delivering power efficiently and reliably to both the system and the accelerators1

Power Configurations1

Power-on mode for AC power recovery, ACPI Power Management4

Power Supplies11

2800W Titanium 200-240VAC or 240VDC; 3200W Titanium 277VAC or 260-400VDC; redundant, hot-swap12800W Titanium, 200-240VAC or 240VDC, redundant, hot-swap13000W Titanium (B200 config) or 2800W Titanium (H200 config), 200-240VAC or 240VDC, hot-swap redundant; 3+3 fault-tolerant or 5+1 redundancy policies; PSU cord: Redundant 86mm, C21 connector13200W Titanium 200-240VAC or 240VDC (multi-capacity: 3200W at 220.1-240VAC or 2900W at 200-220VAC); 3200W Titanium 277VAC or 336VDC; 2400W Titanium 200-240VAC or 240VDC; redundant, hot-swap13200W Titanium 277-305VAC or 336 HVDC; 2800W Titanium 200-240VAC or 240 HVDC; 2400W Platinum 100-240VAC or 240 HVDC; all hot-swap redundant1

Power Supply1

6x 2700W Redundant (4+2) Titanium Level (96%) power supplies4

Processor11

Dual AMD EPYC 9005/9004 Series processors; up to 192C/384T4Two 5th Generation Intel Xeon Scalable processors, up to 64 cores each, up to 350W TDP2One 4th or 5th Generation Intel Xeon Scalable processor (5nm), up to 60 cores, up to 270W TDP1One AMD EPYC 8004 (Siena, Zen4c) processor, 8 to 64 cores, TDP up to 200W; or one AMD EPYC 8005 (Sorano, Zen5) processor, 8 to 84 cores, TDP up to 225W1Two 4th or 5th Generation Intel Xeon Scalable processors, up to 64 cores per processor, up to 350W TDP1

Processor Features1

DDR5 memory up to 5600 MT/s, PCIe Gen5 up to 80 lanes/socket, up to 4x Intel UPI at 20GT/s, Intel TDX for confidential computing2

Processor SKUs Supported1

8592+ (64C, 1.9GHz, 320MB Cache, 350W); 8580 (60C, 2.0GHz, 300MB, 350W); 8570 (56C, 2.1GHz, 300MB, 350W); 8568Y+ (48C, 2.3GHz, 300MB, 350W); 8562Y+ (32C, 2.8GHz, 60MB, 300W)2

Product SKU1

AS-5126GS-TNRT21

Product SKUs1

AS-5126GS-TNRT; AS-5126GS-TNRT-01-G2 (Gold Series pre-configured variant)3

Rack Requirement1

IR5000 rack required1

Rails1

Stab-in sliding rails only (B38), tool-less install for 19" EIA-310-E square/unthreaded round hole 4-post racks; partial system extension for serviceability2

Recommended Support5

HPE Tech Care Service or HPE Complete Care Service for enhanced response and proactive support5ProSupport Plus for Infrastructure recommended for XE-series (4-hour onsite response, proactive maintenance, Technical Customer Success Manager, third-party software support)3Dell ProSupport Plus for critical systems, or Dell ProSupport for premium hardware/software support; consulting and deployment offerings available1ProSupport Plus for Infrastructure (4-hour onsite response, proactive maintenance, Technical Customer Success Manager, third-party software support)1ProSupport Plus for Infrastructure — proactive/predictive support, assigned customer advocate, 24/7 senior engineer access, automatic case creation, Severity 1 critical response1

Security10

Cryptographically signed firmware, Data at Rest Encryption (SEDs with local/external key mgmt), Secure Boot, Secured Component Verification, Secure Erase, Silicon Root of Trust, System Lockdown (iDRAC Enterprise/Datacenter), TPM 2.0 FIPS/CC-TCG certified2Cryptographically signed firmware, Data at Rest Encryption (SEDs with local or external key mgmt), Secure Boot, Secured Component Verification (hardware integrity check), Secure Erase, Silicon Root of Trust, System Lockdown (requires iDRAC9 Enterprise or Datacenter), TPM 2.0 FIPS/CC-TCG certified/TPM 2.0 China NationZ1Cryptographically signed firmware, Data at Rest Encryption (SEDs with local/external key mgmt), Secure Boot, Secured Component Verification, Secure Erase, Silicon Root of Trust, System Lockdown (iDRAC9 Enterprise/Datacenter), TPM 2.0 FIPS/CC-TCG certified/China NationZ1HPE Silicon Root of Trust anchoring server firmware to the Intel Secure Processor, bezel lock kit, intrusion detection cable kit, TPM1HPE Silicon Root of Trust with zero-trust firmware integrity checking, default IDevID certificates, embedded TPM 2.0, optional locking bezel kit, optional intrusion detection kit; iLO 7 supports quantum-resistant (PQC) algorithms and signs Gen12 firmware with CNSA 2.0-approved algorithms1

Standard Warranty2

3-year hardware warranty covering repair/replacement of defective components (hardware only, no software support included)53-year parts, 3-year labour, 3-year onsite support with next business day response5

Storage2

Front up to 8x E3.S Gen5 NVMe SSDs (max ~122.88TB); internal boot BOSS-N1 with dual M.2 NVMe (HWRAID 1)1SFF NVMe and EDSFF (E3.S) drive options; NS204i-u front cage kit available for two hot-pluggable NVMe M.2 boot devices1

Storage Controller1

Internal Boot: BOSS-N1 (HWRAID 1, 2x M.2 SSDs)2

Storage Controllers3

HPE MR216i-p Gen11 and MR416i-p Gen11 plug-in controllers; HPE Smart Array E208e-p SR Gen10 external controller1Internal: PERC H965i (not supported with Intel Gaudi3); Internal Boot: BOSS-N1 (HWRAID 1, 2x M.2 SSDs)1Internal: PERC H965i, PERC H755, PERC H755N, PERC H355, HBA355i, HBA465i; Internal Boot: BOSS-N1 (HWRAID, 2x M.2 NVMe SSDs) or USB; External HBA (non-RAID): HBA355e, HBA465e, H965e; Software RAID: S1601

Superchip1

NVIDIA GH200 Grace Hopper Superchip; single-superchip or dual-superchip NVIDIA GH200 NVL2 configuration with NVLink between the two GH2001

Supported Operating Systems3

Canonical Ubuntu Server LTS, Red Hat Enterprise Linux3Canonical Ubuntu Server LTS, Red Hat Enterprise Linux, SUSE Linux Enterprise Server, VMware ESXi1Initial certification plans cover Red Hat Enterprise Linux 9.4, Canonical Ubuntu 24.04, and SUSE Linux Enterprise Server 15 SP5 QU11

Supported Operating Systems and Hypervisors2

Canonical Ubuntu Server LTS, Microsoft Windows Server with Hyper-V, Red Hat Enterprise Linux, SUSE Linux Enterprise Server, VMware ESXi1Canonical Ubuntu Server LTS, Red Hat Enterprise Linux, SUSE Linux Enterprise Server, VMware ESXi1

System Weight2

Fully populated with H200 GPUs: 91.63kg (202.00lb); Fully populated with B200 GPUs: 95.6kg (210.76lb) — recommend server-lift for weights ≥121lb1H200 config: 91.63kg (202.00lb); B200 config: 95.60kg (206.35lb/210.76lb per Tech Guide) — recommend server-lift for weights ≥121lb1

TDP Support1

Up to 500W TDP CPUs4

Target Workloads2

Enterprise AI inferencing at scale, focused fine-tuning, high-performance computing1Machine learning, deep learning, AI training and inference, advanced engineering applications, graphics-intensive workloads1

Tools1

IPMI1

Top Workloads1

Edge AI and computer vision, containers, hybrid cloud, VDI, virtualisation1

USB1

2x ports (rear)4

Validated GPU Options1

NVIDIA RTX PRO 6000 Blackwell Server Edition (up to 8 double-wide), NVIDIA H200 NVL, NVIDIA H100 NVL, NVIDIA L40S, NVIDIA L20, NVIDIA L4 (single-wide)1

ServersGPU ServersDell EMC GPU servers

Request Quote

Get Quote

Quote OnlyNew

Dell

Dell PowerEdge XE9680 GPU Server

ServersGPU ServersDell EMC GPU servers

Request Quote

Get Quote

Quote OnlyNew

Dell

Dell PowerEdge XE8640 GPU Server

ServersGPU ServersDell EMC GPU servers

Request Quote

Get Quote

Quote OnlyNew

Dell

Dell PowerEdge R760xa GPU Server

ServersGPU ServersDell EMC GPU servers

Request Quote

Get Quote

Your Cart

GPU Server Solutions AI/ML Servers

Browse by Type

Supermicro 5U GPU Server (AS-5126GS-TNRT)

Supermicro AS-5126GS-TNRT H14 5U GPU SuperServer

HPE ProLiant DL145 Gen11 GPU Server

HPE ProLiant DL320 Gen11 GPU Server

HPE ProLiant DL380a Gen11 GPU Server

HPE ProLiant DL384 Gen12 GPU Servers

HPE ProLiant DL380a Gen12 GPU Server

Dell PowerEdge XE9680L GPU Server

Dell PowerEdge XE9685L GPU Server

Dell PowerEdge XE9680 GPU Server

Dell PowerEdge XE8640 GPU Server

Dell PowerEdge R760xa GPU Server