All Products

Browse 162 products across all categories and brands

View by Category:All Categories NVIDIA Data Center GPUs AMD Instinct Accelerators Intel Gaudi AI Accelerators Google TPU Accelerators Amazon AI Chips Server CPUs AI Servers & Platforms Networking & Interconnects AI Memory & HBM Enterprise Storage

Compare Products Request Bulk Pricing

Brand

Sort By

Browse All Brands

162 results

In Stock

Amazon Inferentia 2

AWS's 2nd-generation AI inference chip for cost-effective, low-latency model deployment.

ArchitectureInferentia 2

Memory- (AWS Exclusive)

TDP-

On Order

Amazon Trainium 2

Amazon's 2nd-generation AI training chip for EC2 Trn2 instances with ultra-high performance.

ArchitectureTrainium 2

Memory- (AWS Exclusive)

TDP-

Pre-Order

Amazon Trainium 3

Amazon's 3rd-generation AI training chip for next-gen EC2 Trn3 instances with 3x Trainium 2 performance.

ArchitectureTrainium 3

Memory- (AWS Exclusive)

TDP-

In Stock

AMD EPYC 7763

64-core Zen 3 server processor with 280W TDP for legacy enterprise and HPC deployments.

ArchitectureZen 3

Memory256MB L3 Cache

TDP280W

Pre-Order

AMD EPYC 9175F

16-core frequency-optimized Zen 5 server processor for maximum per-core performance in specialized workloads.

ArchitectureZen 5

Memory128MB L3 Cache

TDP-

In Stock

AMD EPYC 9374F

32-core high-frequency Zen 4 server processor with 320W TDP for frequency-sensitive workloads.

ArchitectureZen 4

Memory256MB L3 Cache

TDP320W

Pre-Order

AMD EPYC 9375F

32-core frequency-optimized Zen 5 server processor for single-threaded and latency-critical workloads.

ArchitectureZen 5

Memory256MB L3 Cache

TDP-

In Stock

AMD EPYC 9454

48-core Zen 4 server processor with 290W TDP for efficient enterprise data center deployments.

ArchitectureZen 4

Memory256MB L3 Cache

TDP290W

Pre-Order

AMD EPYC 9475F

48-core frequency-optimized Zen 5 server processor for high-performance database and enterprise applications.

ArchitectureZen 5

Memory256MB L3 Cache

TDP-

In Stock

AMD EPYC 9554

64-core Zen 4 server processor with 360W TDP for balanced enterprise compute.

ArchitectureZen 4

Memory256MB L3 Cache

TDP360W

Pre-Order

AMD EPYC 9575F

64-core frequency-optimized Zen 5 server processor for latency-sensitive and database workloads.

ArchitectureZen 5

Memory256MB L3 Cache

TDP-

In Stock

AMD EPYC 9654

96-core Zen 4 server processor with 360W TDP for enterprise data centers and cloud infrastructure.

ArchitectureZen 4

Memory384MB L3 Cache

TDP360W

In Stock

AMD EPYC 9654P

96-core single-socket optimized Zen 4 server processor with 360W TDP for cost-effective deployments.

ArchitectureZen 4

Memory384MB L3 Cache

TDP360W

Pre-Order

AMD EPYC 9655

96-core Zen 5 server processor delivering exceptional throughput for enterprise and cloud workloads.

ArchitectureZen 5

Memory384MB L3 Cache

TDP-

Pre-Order

AMD EPYC 9675

96-core Zen 5 server processor with high core density for enterprise and cloud infrastructure.

ArchitectureZen 5

Memory384MB L3 Cache

TDP-

In Stock

AMD EPYC 9754

112-core Bergamo server processor with Zen 4c architecture for efficient cloud-scale computing.

ArchitectureZen 4c (Bergamo)

Memory256MB L3 Cache

TDP320W

Pre-Order

AMD EPYC 9755 Turin

128-core flagship server processor with Zen 5 architecture, 500W TDP, and SP5 socket for maximum data center performance.

ArchitectureZen 5

Memory512MB L3 Cache

TDP500W

In Stock

AMD EPYC 9854

128-core Bergamo server processor with Zen 4c architecture for high-density cloud-native workloads.

ArchitectureZen 4c (Bergamo)

Memory256MB L3 Cache

TDP320W

In Stock

AMD Instinct MI100 Accelerator

First-gen CDNA accelerator with 32GB HBM2 memory for HPC and scientific computing.

ArchitectureCDNA 1

Memory32GB HBM2

TDP300W

In Stock

AMD Instinct MI210 Accelerator

Single-GPU CDNA 2 accelerator with 64GB HBM2e for mainstream HPC and AI inference workloads.

ArchitectureCDNA 2

Memory64GB HBM2e

TDP300W

Limited

AMD Instinct MI250 Accelerator

HPC-optimized accelerator with 128GB HBM2e memory for scientific computing and simulation workloads.

ArchitectureCDNA 2

Memory128GB HBM2e

TDP500W

In Stock

AMD Instinct MI300A APU

Revolutionary APU combining Zen 4 CPU cores and CDNA 3 GPU compute with 128GB unified HBM3 memory.

ArchitectureCDNA 3 + Zen 4

Memory128GB Unified HBM3

TDP-

In Stock

AMD Instinct MI300X Accelerator

Purpose-built AI accelerator with 192GB HBM3 memory, 5.2 TB/s bandwidth, and 750W TDP for HPC and AI.

ArchitectureCDNA 3

Memory192GB HBM3

TDP750W

In Stock

AMD Instinct MI325X Accelerator

High-capacity AI accelerator with 288GB HBM3 memory for large model training and inference.

ArchitectureCDNA 3

Memory288GB HBM3

TDP-

Pre-Order

AMD Instinct MI350X Accelerator

Flagship AI accelerator with 288GB HBM3e memory and CDNA 4 architecture for large-scale training and inference.

ArchitectureCDNA 4

Memory288GB HBM3e

TDP-

Pre-Order

AMD Instinct MI600 Accelerator

Next-gen CDNA 4 accelerator with 256GB HBM4 memory for exascale AI training and inference.

ArchitectureCDNA 4

Memory256GB HBM4

TDP-

In Stock

AMD Pensando DPU

P4-programmable data processing unit with 200Gbps throughput for infrastructure acceleration.

ArchitectureP4 Programmable

Memory-

TDP-

In Stock

AMD Radeon Pro W7600

Entry-level professional workstation GPU with 8GB GDDR6 for CAD, multi-display, and lightweight visualization.

ArchitectureRDNA 3

Memory8GB GDDR6

TDP150W

In Stock

AMD Radeon Pro W7700

Professional workstation GPU with 16GB GDDR6 ECC for mainstream CAD, visualization, and AI inference.

ArchitectureRDNA 3

Memory16GB GDDR6 ECC

TDP190W

In Stock

AMD Radeon Pro W7800

Mid-range workstation GPU with 32GB GDDR6 for professional visualization and AI inference.

ArchitectureRDNA 3

Memory32GB GDDR6

TDP260W

In Stock

AMD Radeon Pro W7900

Flagship workstation GPU with 48GB GDDR6 ECC for professional AI, rendering, and visualization.

ArchitectureRDNA 3

Memory48GB GDDR6 ECC

TDP295W

In Stock

Ampere Altra

128-core cloud-native Arm server processor with DDR4 for hyperscale cloud workloads.

ArchitectureAltra

MemoryDDR4-3200

TDP250W

In Stock

Ampere Altra Max

128-core cloud-native Arm processor with DDR4 and enhanced frequency for cloud and edge workloads.

ArchitectureAltra Max

MemoryDDR4-3200

TDP280W

In Stock

AmpereOne

192-core cloud-native Arm server processor with DDR5 and PCIe 5.0 for hyperscale data centers.

ArchitectureAmpereOne

MemoryDDR5

TDP-

In Stock

ASUS ESC N8-E11

Purpose-built AI server with 8x GPU support for enterprise deep learning.

Form Factor4U

GPUUp to 8x NVIDIA H100/H200/B200

CPU2x Intel Xeon Scalable (4th/5th Gen)

In Stock

ASUS RS720A-E12

2U rack server with dual AMD EPYC for database, virtualization, and enterprise workloads.

Form Factor2U

GPUUp to 2x single-width GPUs

CPU2x AMD EPYC 9004 series

In Stock

AWS Graviton4

AWS's 4th-generation custom Arm processor for EC2 with 30% better compute performance over Graviton3.

ArchitectureGraviton4

MemoryDDR5

TDP-

In Stock

Broadcom Jericho 3AI

AI-optimized Ethernet switch with in-network computing for distributed AI training workloads.

TypeAI Ethernet Switch

SpeedUp to 800GbE per port

Ports48x 800GbE

In Stock

Broadcom P2100G Ethernet Adapter

200GbE Ethernet NIC with RDMA RoCEv2 for high-performance data center connectivity.

TypeEthernet NIC

Speed200 Gbps

Ports2x 100GbE / 1x 200GbE

In Stock

Broadcom Stingray PS1100R SmartNIC

100GbE SmartNIC with hardware-accelerated network processing and security offload.

TypeSmartNIC

Speed100 Gbps

Ports2x 50GbE / 1x 100GbE

In Stock

Broadcom Tomahawk 6

World's highest-bandwidth Ethernet switch with 51.2 Tbps switching capacity for AI and HPC data center fabrics.

TypeEthernet Switch ASIC

Speed51.2 Tbps

Ports64x 800GbE / 128x 400GbE

In Stock

Cisco Nexus 9800

51.2T modular data center switch for AI/ML fabrics and cloud-scale networking.

TypeModular Switch

Speed51.2 Tbps

PortsUp to 64x 800GbE

In Stock

Cisco Silicon One G100

Unified programmable network processor for routing and switching at 25.6 Tbps.

TypeNetwork Processor

Speed25.6 Tbps

Ports64x 400GbE

In Stock

Cisco UCS Fabric Interconnect M6120

Next-generation fabric interconnect for Cisco UCS and HyperFlex infrastructure management.

TypeFabric Interconnect

Speed100 Gbps uplinks

Ports48x 25GbE + 8x 100GbE

On Order

CXL Memory Module

CXL-attached memory module for memory expansion beyond traditional DIMM slots.

TypeCXL Memory Module

Capacity256GB / 512GB

SpeedCXL 2.0 32GT/s

In Stock

Dell PowerEdge R660

1U density-optimized server with Intel Xeon 5th Gen for space-constrained data centers.

Form Factor1U

GPUNo GPU support

CPU2x 5th Gen Intel Xeon Scalable

In Stock

Dell PowerEdge R760

Versatile 2U general purpose server with Intel Xeon 5th Gen processors for enterprise workloads.

Form Factor2U

GPUUp to 2x single-width GPUs

CPU2x 5th Gen Intel Xeon Scalable

In Stock

Dell PowerEdge XE8640

Scalable 4-way GPU server for enterprise AI and accelerated compute workloads.

Form FactorTower

GPUUp to 4x NVIDIA H100/H200/B200

CPU2x Intel Xeon Scalable (4th/5th Gen)

In Stock

Dell PowerEdge XE9680

Enterprise AI server with 8-way GPU support for large-scale model training and inference.

Form FactorTower

GPUUp to 8x NVIDIA H100/H200/B200

CPU2x 4th Gen Intel Xeon Scalable

In Stock

Foxconn AI GPU Platform

High-performance AI acceleration platform with 8x GPU support.

Form Factor4U

GPUUp to 8x NVIDIA H100/H200/B200

CPU2x Intel Xeon Scalable

In Stock

GIGABYTE G292-Z44

2U GPU server with 4x GPU support for AI training, HPC, and deep learning workloads.

Form Factor2U

GPUUp to 4x NVIDIA H100/H200

CPU2x AMD EPYC 9004 series

In Stock

GIGABYTE G593 Series

High-density 4U AI server with 8x GPU support for accelerated computing.

Form Factor4U

GPUUp to 8x NVIDIA H100/H200/B200

CPU2x Intel Xeon Scalable (4th/5th Gen)

In Stock

Google TPU v5e

Cost-optimized Google TPU v5e for inference and fine-tuning of medium-sized AI models.

ArchitectureTPU v5e

Memory- (Google Cloud Exclusive)

TDP-

In Stock

Google TPU v5p

High-performance Google TPU v5p for large-scale AI training with 4x TPU v5e performance.

ArchitectureTPU v5p

Memory- (Google Cloud Exclusive)

TDP-

On Order

Google TPU v6

Google's 6th-generation Tensor Processing Unit for AI training and inference in Google Cloud.

ArchitectureTPU v6

Memory- (Google Cloud Exclusive)

TDP-

Pre-Order

Google TPU v7

Google's 7th-generation TPU with breakthrough AI performance for next-gen models.

ArchitectureTPU v7

Memory- (Google Cloud Exclusive)

TDP-

In Stock

HPE Cray XD670

Supercomputing-class AI server with 8x GPU support and liquid cooling readiness.

Form FactorTower

GPUUp to 8x NVIDIA H100/H200/B200

CPU2x AMD EPYC (4th/5th Gen)

In Stock

HPE Edgeline 8000

Rugged edge AI server delivering GPU-accelerated inference at the network edge.

Form FactorEdge / 4U

GPUUp to 4x single-width GPUs

CPU2x Intel Xeon Scalable or AMD EPYC

In Stock

HPE ProLiant DL380 Gen12

Versatile enterprise server with next-gen Intel Xeon and expansive memory capacity.

Form Factor2U

GPUUp to 3x single-width GPUs

CPU2x Intel Xeon Scalable (5th Gen)

In Stock

HPE ProLiant DL385 Gen11

AMD EPYC-powered 2U rack server optimized for virtualization, database, and cloud workloads.

Form Factor2U

GPUUp to 2x single-width GPUs

CPU2x AMD EPYC 9004 series

In Stock

Inspur NF5280M7

2U dual-socket server with Intel Xeon 5th Gen for enterprise and cloud deployments.

Form Factor2U

GPUUp to 2x single-width GPUs

CPU2x 5th Gen Intel Xeon Scalable

In Stock

Inspur NF5688 Series

High-performance AI server with 8x GPU support for large-scale model training.

Form Factor4U

GPUUp to 8x NVIDIA H100/H200/B200

CPU2x Intel Xeon Scalable (4th/5th Gen)

In Stock

Intel Arc A770 GPU

Intel Arc A770 GPU with 16 GB GDDR6 delivers workstation-class graphics and compute for professional visualization and entry-level AI.

ArchitectureAlchemist

Memory16 GB GDDR6 (ECC)

TDP225W

In Stock

Intel Arc B580 GPU

Next-gen Intel Arc B580 GPU with 12GB GDDR6 and Battlemage architecture for gaming and AI workloads.

ArchitectureBattlemage

Memory12GB GDDR6

TDP190W

In Stock

Intel Arc Pro A60

Intel Arc Pro A60 with 12 GB GDDR6 delivers reliable professional graphics for certified ISV workflows and multi-display deployments.

ArchitectureAlchemist

Memory12 GB GDDR6

TDP130W

In Stock

Intel Data Center GPU Flex 170

Data center GPU with 16GB GDDR6 for media transcoding, cloud gaming, and AI inference.

ArchitectureFlex

Memory16GB GDDR6

TDP150W

In Stock

Intel Gaudi 2 AI Accelerator

Intel Gaudi 2 AI accelerator with 96 GB HBM2e delivers efficient deep-learning training and inference at scale.

ArchitectureGaudi 2

Memory96 GB HBM2e

TDP450W (PCIe) / 600W (OAM)

In Stock

Intel Gaudi 2E AI Accelerator

Enhanced Gaudi 2 accelerator with 96GB HBM2e memory for cost-effective AI training and inference.

ArchitectureGaudi 2

Memory96GB HBM2e

TDP450W (PCIe) / 600W (OAM)

On Order

Intel Gaudi 3 AI Accelerator

Intel Gaudi 3 AI accelerator delivers 144 GB HBM2e memory and 600W TDP for large-scale AI training and inference.

ArchitectureGaudi 3

Memory144 GB HBM2e

TDP600W

On Order

Intel Xeon 6300 Series

Intel Xeon 6300 Series with Granite Rapids architecture for entry-level enterprise servers.

ArchitectureGranite Rapids

MemoryDDR5-5600, 8 channels

TDPUp to 300W

On Order

Intel Xeon 6500 Series

Intel Xeon 6500 Series with Granite Rapids architecture for scalable enterprise computing.

ArchitectureGranite Rapids

MemoryDDR5-6400, 8 channels

TDPUp to 350W

On Order

Intel Xeon 6500Y

32-core efficient Granite Rapids processor for power-optimized enterprise and cloud infrastructure.

ArchitectureGranite Rapids

MemoryDDR5-5600, 8 channels

TDP-

On Order

Intel Xeon 6700 Series

Intel Xeon 6700 Series processors combine Granite Rapids performance cores with balanced efficiency for scalable enterprise computing.

ArchitectureGranite Rapids

MemoryDDR5-5600, 8 channels

TDPUp to 350W

On Order

Intel Xeon 6710P

12-core E-core Granite Rapids processor for entry-level and edge-optimized data center deployments.

ArchitectureGranite Rapids

MemoryDDR5-4800, 8 channels

TDP-

On Order

Intel Xeon 6760P

32-core E-core Granite Rapids processor for cost-efficient scale-out and cloud-native infrastructure.

ArchitectureGranite Rapids

MemoryDDR5-5600, 8 channels

TDP-

On Order

Intel Xeon 6770P

48-core E-core Granite Rapids processor for efficient cloud-native and throughput-optimized data center workloads.

ArchitectureGranite Rapids

MemoryDDR5-5600, 8 channels

TDP-

On Order

Intel Xeon 6780P

64-core E-core Granite Rapids processor optimized for high-throughput cloud-native and scale-out workloads.

ArchitectureGranite Rapids

MemoryDDR5-5600, 8 channels

TDP-

On Order

Intel Xeon 6900 Series

Intel Xeon 6900 Series processors deliver up to 128 performance cores with Granite Rapids architecture for the most demanding enterprise workloads.

ArchitectureGranite Rapids

MemoryDDR5-6400, 12 channels

TDPUp to 500W

On Order

Intel Xeon 6920P

24-core P-core Granite Rapids processor for entry-level enterprise servers with strong per-core performance.

ArchitectureGranite Rapids

MemoryDDR5-5600, 8 channels

TDP-

On Order

Intel Xeon 6930P

36-core P-core Granite Rapids processor for balanced enterprise compute with strong per-core performance.

ArchitectureGranite Rapids

MemoryDDR5-5600, 8 channels

TDP-

On Order

Intel Xeon 6940P

48-core P-core Granite Rapids processor for cost-effective enterprise server deployments.

ArchitectureGranite Rapids

MemoryDDR5-6400, 8 channels

TDP-

On Order

Intel Xeon 6950P

60-core P-core Granite Rapids processor for mainstream enterprise compute and virtualization.

ArchitectureGranite Rapids

MemoryDDR5-6400, 12 channels

TDP-

On Order

Intel Xeon 6960P

72-core P-core Granite Rapids processor for high-performance enterprise and HPC data center workloads.

ArchitectureGranite Rapids

MemoryDDR5-6400, 12 channels

TDP-

On Order

Intel Xeon 6980P

Intel Xeon 6980P is a flagship 128-core Granite Rapids processor designed for ultra-dense data center compute.

ArchitectureGranite Rapids

MemoryDDR5-6400, 12 channels

TDP500W

In Stock

Intel Xeon 8490H

Intel Xeon 8490H offers 60 Sapphire Rapids cores with built-in AMX AI acceleration for enterprise and cloud workloads.

ArchitectureSapphire Rapids

MemoryDDR5-4800, 8 channels

TDP350W

Limited

Intel Xeon Max 9480

Intel Xeon Max 9480 integrates 64 GB of HBM2e memory on-package for memory-bandwidth-intensive HPC and AI workloads.

ArchitectureSapphire Rapids

Memory64 GB HBM2e on-package + DDR5-4800

TDP350W

In Stock

Intel Xeon w9-3595X

60-core workstation processor with Sapphire Rapids architecture for professional content creation and AI.

ArchitectureSapphire Rapids

MemoryDDR5-4800, 8 channels

TDP350W

In Stock

Kioxia CM7-V3 NVMe SSD

PCIe Gen5 enterprise NVMe SSD with BiCS FLASH for data center workloads.

Capacity3.84TB / 7.68TB / 15.36TB

Read12,000 MB/s

InterfacePCIe Gen5 x4

In Stock

Lenovo ThinkSystem SR630 V3

1U general purpose server with Intel Xeon 5th Gen for enterprise and cloud workloads.

Form Factor1U

GPUNo GPU support

CPU2x 5th Gen Intel Xeon Scalable

In Stock

Lenovo ThinkSystem SR685a V3

Versatile 4-way GPU server powered by AMD EPYC for AI and accelerated analytics.

Form Factor4U

GPUUp to 4x NVIDIA H100/H200/B200

CPU2x AMD EPYC (4th/5th Gen)

In Stock

Lenovo ThinkSystem SR780a V3

Flagship 6U AI server with 8x GPU support for enterprise deep learning workloads.

Form Factor6U

GPUUp to 8x NVIDIA H100/H200/B200

CPU2x Intel Xeon Scalable (4th/5th Gen)

In Stock

Marvell Aquila 2 Memory Controller

High-performance DDR5 memory controller for server and AI accelerator platforms.

TypeMemory Controller

SpeedDDR5-6400+ MT/s

PortsMulti-Channel DDR5

In Stock

Marvell OCTEON 10 DPU

Arm-based DPU with hardware acceleration for networking, storage, and security offload.

TypeData Processing Unit

Speed200 Gbps

Ports2x 100GbE / 1x 200GbE

In Stock

Marvell Teralynx 10

51.2 Tbps Ethernet switch with industry-leading power efficiency for cloud and AI data centers.

TypeEthernet Switch ASIC

Speed51.2 Tbps

Ports64x 800GbE / 128x 400GbE

In Stock

Micron 7450 NVMe SSD

PCIe Gen4 enterprise NVMe SSD with 6.4TB capacity and balanced read/write performance.

Capacity800GB / 1.6TB / 3.2TB / 6.4TB

Read5,000 MB/s

InterfacePCIe Gen4 x4

In Stock

Micron 9550 NVMe SSD

PCIe Gen5 data center SSD with up to 14 GB/s read for AI and HPC workloads.

Capacity3.84TB / 7.68TB / 15.36TB / 30.72TB

Read14,000 MB/s

InterfacePCIe Gen5 x4

In Stock

Micron DDR5 RDIMM

Enterprise DDR5 RDIMM for next-generation server platforms.

TypeDDR5 RDIMM

Capacity16GB / 32GB / 64GB / 128GB

Speed5600 MT/s

In Stock

Micron HBM3

Micron HBM3 with 24GB capacity and 819 GB/s bandwidth for AI accelerator platforms.

TypeHBM3

Capacity24GB per stack

Speed6.4 Gbps

In Stock

Micron HBM3E

Micron HBM3E with industry-leading 1.2+ TB/s bandwidth for AI and HPC.

TypeHBM3E

Capacity36GB per stack

Speed9.6 Gbps

Pre-Order

MRDIMM (Multiplexed Rank DIMM)

Next-generation multiplexed rank DIMM for 8800+ MT/s server memory performance.

TypeMRDIMM

Capacity128GB / 256GB

Speed8800+ MT/s

In Stock

NVIDIA A10 GPU

Versatile data center GPU with 24GB GDDR6 for AI inference, graphics, and video analytics.

ArchitectureAmpere

Memory24GB GDDR6

TDP150W

In Stock

NVIDIA A100 PCIe Tensor Core GPU

PCIe variant of the A100 with 80GB HBM2e and 300W TDP for broad server compatibility.

ArchitectureAmpere

Memory80GB HBM2e

TDP300W

In Stock

NVIDIA A100 SXM Tensor Core GPU

Flagship SXM variant of the A100 with 80GB HBM2e memory and 400W TDP for AI training and HPC.

ArchitectureAmpere

Memory80GB HBM2e

TDP400W

In Stock

NVIDIA A100 Tensor Core GPU

Industry-defining data center GPU with 80GB HBM2e and 3rd-gen Tensor Cores for AI training and HPC.

ArchitectureAmpere

Memory80GB HBM2e

TDP300W (PCIe) / 400W (SXM4)

In Stock

NVIDIA A30 GPU

Mainstream AI training and inference GPU with 24GB HBM2e and MIG for balanced enterprise deployments.

ArchitectureAmpere

Memory24GB HBM2e

TDP300W

In Stock

NVIDIA A800 GPU

Ampere-based GPU with 80GB HBM2e and reduced interconnect for availability in export-controlled regions.

ArchitectureAmpere

Memory80GB HBM2e

TDP400W

Pre-Order

NVIDIA B100 Tensor Core GPU

High-performance Blackwell GPU with 192GB HBM3e memory and FP4 support for efficient AI training.

ArchitectureBlackwell

Memory192GB HBM3e

TDP700W

Pre-Order

NVIDIA B200 Tensor Core GPU

Flagship Blackwell GPU with 384GB HBM3e memory and 10 TB/s bandwidth for extreme-scale AI.

ArchitectureBlackwell

Memory384GB HBM3e

TDP1000W

Pre-Order

NVIDIA B300 Tensor Core GPU

Next-generation Blackwell GPU with 288GB HBM3e memory and native FP4 tensor core support for generative AI.

ArchitectureBlackwell

Memory288GB HBM3e

TDP900W

In Stock

NVIDIA BlueField-2 DPU

Second-gen DPU with 200GbE connectivity for infrastructure offload and zero-trust security.

TypeData Processing Unit

Speed200 Gbps

Ports2x 100GbE / 1x 200GbE

In Stock

NVIDIA BlueField-3 DPU

Third-gen data processing unit with 400GbE networking and programmable Arm cores.

TypeData Processing Unit

Speed400Gb/s

Ports2x 200GbE / 1x 400GbE

In Stock

NVIDIA ConnectX-7 NIC

400GbE SmartNIC with RDMA, GPUDirect, and advanced virtualization offload.

TypeSmart NIC

Speed400 Gbps

Ports1x QSFP112 / 2x 200GbE

In Stock

NVIDIA ConnectX-8 NIC

400Gb/s smart NIC with DPU capabilities for AI and cloud workloads.

TypeSmart NIC

Speed400Gb/s

Ports1x QSFP112 / 2x 200GbE

Pre-Order

NVIDIA GB200 Grace Blackwell Superchip

Flagship superchip combining Grace CPU with dual Blackwell GPUs via NVLink 5.0 for trillion-parameter AI workloads.

ArchitectureBlackwell

Memory384GB HBM3e + 480GB LPDDR5X

TDP1000W

In Stock

NVIDIA GH200 Grace Hopper Superchip

Integrated superchip combining Grace CPU with Hopper GPU via NVLink-C2C for HPC and AI convergence.

ArchitectureHopper + Grace

Memory96GB HBM3 + 528GB LPDDR5X

TDP1000W

Pre-Order

NVIDIA Grace CPU

72-core ARM-based server CPU with 480GB LPDDR5X and NVLink-C2C for HPC and AI convergence.

ArchitectureARM Neoverse V2

Memory480GB LPDDR5X

TDP155W

In Stock

NVIDIA H100 NVL PCIe Tensor Core GPU

PCIe dual-GPU Hopper accelerator with 188GB HBM3 for broad server compatibility and LLM inference.

ArchitectureHopper

Memory188GB HBM3 (2x 94GB)

TDP600W

In Stock

NVIDIA H100 NVL Tensor Core GPU

Dual-GPU Hopper accelerator with 188GB HBM3 (2x 94GB) for power-efficient LLM inference and training.

ArchitectureHopper

Memory188GB HBM3 (2x 94GB)

TDP600W

In Stock

NVIDIA H100 Tensor Core GPU

Industry-standard AI training GPU with 80GB HBM3 and 3.35 TB/s bandwidth in SXM5 form factor.

ArchitectureHopper

Memory80GB HBM3

TDP700W

In Stock

NVIDIA H200 Tensor Core GPU

Advanced Hopper GPU with 141GB HBM3e memory and 4.8 TB/s bandwidth for large model inference.

ArchitectureHopper

Memory141GB HBM3e

TDP700W

In Stock

NVIDIA H800 GPU

Hopper-based data center GPU with 80GB HBM3 and reduced interconnect for regulated markets.

ArchitectureHopper

Memory80GB HBM3

TDP700W

In Stock

NVIDIA L4 GPU

Energy-efficient data center GPU with 24GB GDDR6 for AI inference, edge computing, and video.

ArchitectureAda Lovelace

Memory24GB GDDR6

TDP72W

In Stock

NVIDIA L40 GPU

Professional-grade data center GPU with 48GB GDDR6 for visual computing, AI inference, and graphics.

ArchitectureAda Lovelace

Memory48GB GDDR6 ECC

TDP300W

In Stock

NVIDIA L40 GPU

Professional data center GPU with 48GB GDDR6 ECC for visual computing, AI inference, and graphics.

ArchitectureAda Lovelace

Memory48GB GDDR6 ECC

TDP300W

In Stock

NVIDIA L40S GPU

Versatile data center GPU with 48GB GDDR6 ECC memory for AI inference, graphics, and video.

ArchitectureAda Lovelace

Memory48GB GDDR6 ECC

TDP350W

In Stock

NVIDIA Quantum Q3400 InfiniBand Switch

NDR 400Gb/s InfiniBand switch for ultra-scale AI supercomputing clusters.

TypeInfiniBand Switch

Speed25.6 Tbps aggregate

Ports64x NDR 400Gb/s

In Stock

NVIDIA RTX 2000 Ada Generation

Compact professional workstation GPU with 16GB GDDR6 ECC for 2D/3D CAD, edge AI, and power-constrained workstations.

ArchitectureAda Lovelace

Memory16GB GDDR6 ECC

TDP70W

In Stock

NVIDIA RTX 3500 Ada Generation

Entry-level professional workstation GPU with 12GB GDDR6 ECC for CAD drafting, visualization, and light AI.

ArchitectureAda Lovelace

Memory12GB GDDR6 ECC

TDP70W

In Stock

NVIDIA RTX 4000 Ada Generation

Entry-level professional Ada GPU with 20GB GDDR6 ECC for CAD, rendering, and AI inference.

ArchitectureAda Lovelace

Memory20GB GDDR6 ECC

TDP130W

In Stock

NVIDIA RTX 4000 Ada Generation

Compact data center Ada GPU with 20GB GDDR6 ECC for edge AI inference, video analytics, and VDI.

ArchitectureAda Lovelace

Memory20GB GDDR6 ECC

TDP130W

In Stock

NVIDIA RTX 4000 Ada Generation

Entry-level professional Ada GPU with 20GB GDDR6 ECC for CAD, rendering, and AI inference.

ArchitectureAda Lovelace

Memory20GB GDDR6 ECC

TDP130W

In Stock

NVIDIA RTX 4000 Ada Generation

Mid-range professional workstation GPU with 20GB GDDR6 ECC for CAD, 3D content creation, and AI inference.

ArchitectureAda Lovelace

Memory20GB GDDR6 ECC

TDP130W

In Stock

NVIDIA RTX 4500 Ada Generation

Mid-range professional GPU with 24GB GDDR6 for CAD, 3D rendering, and AI-accelerated workflows.

ArchitectureAda Lovelace

Memory24GB GDDR6 ECC

TDP200W

In Stock

NVIDIA RTX 5000 Ada Generation

Data center Ada GPU with 32GB GDDR6 ECC for AI inference, graphics rendering, and virtual workstations.

ArchitectureAda Lovelace

Memory32GB GDDR6 ECC

TDP250W

In Stock

NVIDIA RTX 5000 Ada Generation

Mid-range professional GPU with 32GB GDDR6 ECC for workstation AI and graphics.

ArchitectureAda Lovelace

Memory32GB GDDR6 ECC

TDP250W

In Stock

NVIDIA RTX 5000 Ada Generation

Professional workstation GPU with 32GB GDDR6 ECC for CAD, 3D rendering, and AI-accelerated workflows.

ArchitectureAda Lovelace

Memory32GB GDDR6 ECC

TDP250W

In Stock

NVIDIA RTX 6000 Ada Generation

Flagship professional GPU with 48GB GDDR6 ECC memory for AI, rendering, and scientific visualization.

ArchitectureAda Lovelace

Memory48GB GDDR6 ECC

TDP300W

In Stock

NVIDIA RTX 6000 Ada Generation

Flagship professional workstation GPU with 48GB GDDR6 ECC for AI development, rendering, and scientific visualization.

ArchitectureAda Lovelace

Memory48GB GDDR6 ECC

TDP300W

In Stock

NVIDIA Spectrum-X SN5000

AI-optimized Ethernet switch platform with 51.2 Tbps for lossless RoCE fabric.

TypeEthernet Switch

Speed51.2 Tbps

Ports64x 800GbE / 128x 400GbE

In Stock

NVIDIA T4 GPU

Energy-efficient inference GPU with 16GB GDDR6 for ML inference, video transcoding, and VDI workloads.

ArchitectureTuring

Memory16GB GDDR6

TDP70W

Limited

NVIDIA V100 Tensor Core GPU

Pioneering Tensor Core GPU with 32GB HBM2 memory that revolutionized deep learning training.

ArchitectureVolta

Memory32GB HBM2

TDP300W

In Stock

Qualcomm Cloud AI 100

Purpose-built cloud AI inference accelerator delivering up to 400 TOPS for data center inference workloads.

ArchitectureCloud AI 100

MemoryDDR5 / HBM2e

TDP75W-150W

Pre-Order

Qualcomm Data Center CPU

Qualcomm's emerging data center CPU based on Oryon architecture for cloud workloads.

ArchitectureOryon

Memory-

TDP-

In Stock

Quanta AI GPU Server

Open-standard AI server with 8x GPU support for scalable deep learning.

Form Factor4U

GPUUp to 8x NVIDIA H100/H200/B200

CPU2x AMD EPYC (4th/5th Gen)

In Stock

Samsung DDR5 RDIMM

Enterprise DDR5 RDIMM for server platforms with up to 5600 Mbps speed.

TypeDDR5 RDIMM

Capacity32GB / 64GB / 128GB

Speed5600 Mbps

In Stock

Samsung HBM3

Samsung HBM3 memory with 36GB capacity for AI accelerators and HPC platforms.

TypeHBM3

Capacity36GB per stack

Speed6.4 Gbps

In Stock

Samsung HBM3E

Samsung HBM3E with 1.2 TB/s bandwidth for next-generation AI processors.

TypeHBM3E

Capacity36GB per stack

Speed9.8 Gbps

In Stock

Samsung PM1743 NVMe SSD

PCIe Gen5 enterprise SSD with 13 GB/s sequential read for data center workloads.

Capacity3.84TB / 7.68TB / 15.36TB

Read13,000 MB/s

InterfacePCIe Gen5 x4

In Stock

Samsung PM9A3 NVMe SSD

PCIe Gen4 enterprise SSD with up to 15.36TB capacity for read-intensive data center workloads.

Capacity3.84TB / 7.68TB / 15.36TB

Read6,400 MB/s

InterfacePCIe Gen4 x4

In Stock

Samsung PM9D3 NVMe SSD

PCIe Gen5 mainstream enterprise SSD with balanced performance and power efficiency.

Capacity1.92TB / 3.84TB / 7.68TB

Read6,000 MB/s

InterfacePCIe Gen5 x4

In Stock

Seagate FireCuda 540 NVMe SSD

PCIe Gen5 consumer and workstation NVMe SSD with 2TB capacity for creative and gaming workloads.

Capacity1TB / 2TB

Read10,000 MB/s

InterfacePCIe Gen5 x4

In Stock

Seagate Nytro 3530 NVMe SSD

PCIe Gen4 NVMe SSD with advanced security for enterprise storage.

Capacity3.84TB / 7.68TB / 15.36TB

Read6,400 MB/s

InterfacePCIe Gen4 x4

In Stock

SK hynix DDR5 RDIMM

Enterprise DDR5 RDIMM memory running at 5600MT/s for server and workstation platforms.

TypeDDR5 RDIMM

Capacity32GB / 64GB / 128GB

Speed5600 MT/s

In Stock

SK hynix HBM3

High-bandwidth HBM3 memory for AI accelerators with 819 GB/s bandwidth per stack.

TypeHBM3

Capacity24GB per stack

Speed6.4 Gbps

In Stock

SK hynix HBM3E

Industry-leading HBM3E memory with 1.18 TB/s bandwidth per stack for AI accelerators.

TypeHBM3E

Capacity36GB per stack

Speed9.6 Gbps

In Stock

Solidigm D7-P5810 NVMe SSD

High-capacity PCIe Gen5 NVMe SSD for AI data pipelines and content delivery.

Capacity7.68TB / 15.36TB / 30.72TB / 61.44TB

Read7,000 MB/s

InterfacePCIe Gen5 x4

In Stock

Supermicro AS-8125GS-TNHR

Maximum GPU density server supporting 10 double-width GPUs in a 4U form factor.

Form Factor4U

GPUUp to 10x NVIDIA H100/H200/B200

CPU2x AMD EPYC (4th/5th Gen)

In Stock

Supermicro SYS-121C-TN2R

1U single-socket server with Intel Xeon for web hosting, CDN, and virtualization.

Form Factor1U

GPUNo GPU support

CPU1x Intel Xeon Scalable (4th/5th Gen)

In Stock

Supermicro SYS-821GE-TNHR

Dense 2U server with 4x GPU support for accelerated AI and compute workloads.

Form Factor2U

GPUUp to 4x NVIDIA H100/H200/B200

CPU2x Intel Xeon Scalable (4th/5th Gen)

In Stock

WD Ultrastar DC SN655 NVMe SSD

PCIe Gen4 enterprise NVMe SSD optimized for read-intensive cloud workloads.

Capacity3.84TB / 7.68TB / 15.36TB

Read6,800 MB/s

InterfacePCIe Gen4 x4

In Stock

WD Ultrastar DC SN840 NVMe SSD

PCIe Gen4 enterprise NVMe SSD with 15.36TB capacity for read-intensive hyperscale workloads.

Capacity3.84TB / 7.68TB / 15.36TB

Read6,600 MB/s

InterfacePCIe Gen4 x4

In Stock

Wiwynn AI GPU Server

Cloud-optimized AI server with 8x GPU support for hyperscale workloads.

Form Factor4U

GPUUp to 8x NVIDIA H100/H200/B200

CPU2x Intel Xeon Scalable

Chip Configurator

Not sure which chip fits your workload?

Answer 3 quick questions and our AI-powered configurator will recommend the optimal NVIDIA, AMD or Intel chip for your AI training, inference, HPC or professional workload.

Try the Configurator

Workload-matched picks
Budget & performance aware
Backed by certified engineers

How it works

1Pick your workload
2Set budget & performance
3Get matched chips + quote