-
Vendor:Lenovo
Lenovo SR670 | 2U dual-socket Intel Xeon Scalable | GPU-optimized up to 4x DW or 8x SW GPUs | 24x DIMM DDR4 | NVMe drive options | PCIe 3.0 | OCP NIC | Redundant PSUs | XClarity mgmt
GPU-optimized 2U compute platform built for AI training/inference, VDI, and HPC acceleration. Dual Xeon Scalable CPUs, dense DDR4 memory, flexible NVMe/SAS/SATA storage, and multiple double-width or single-width GPU configurations deliver excellent performance per rack unit. Centralized management via XClarity simplifies fleet operations. -
Vendor:Aruba
Aruba S0K89C | L4 24GB GPU accelerator | PCIe Gen4 x16 | low-profile single-slot | AI inference & video transcode
A data center–ready PCIe accelerator built for AI inference, graphics, and high-density media workloads. Compact, low-profile, single-slot design enables efficient scale-out in mainstream servers while delivering strong AI and video processing performance with modest power draw. -
Vendor:Lenovo
Lenovo SR670-V2 | 3U dual-socket Intel Xeon Scalable Gen3 | GPU-optimized up to 8x GPUs (SXM/PCIe) | 32x DIMM DDR4-3200, Optane PMem support | NVMe bays | PCIe 4.0 | OCP 3.0 | Redundant PSUs | XClarity mgmt
Next-gen GPU compute platform engineered for large-scale AI/ML, HPC, and advanced visualization. Dual 3rd Gen Xeon Scalable CPUs, dense DDR4 with Optane PMem support, PCIe 4.0, and options for up to eight accelerators (SXM or PCIe) deliver exceptional performance, bandwidth, and flexibility. XClarity management enables efficient deployment and orchestration. -
Vendor:Dell
Dell T550 | Tower server | 2-socket Xeon Scalable (Gen3) | DDR4 ECC RDIMM/LRDIMM | PCIe Gen4 | NVMe-ready | hot-plug bays | enterprise HW RAID | iDRAC remote mgmt | redundant PSUs | GPU‑capable
An advanced dual-socket tower platform delivering high core counts, PCIe Gen4 bandwidth, and NVMe-ready storage for modern workloads. Designed for AI/ML inference, virtualization, and data-intensive applications, with hot-plug drive options and resilient power. Enterprise RAID, robust security, and out-of-band management simplify deployment and lifecycle operations. Scales with GPUs, high-speed NICs, and fabric adapters to meet future performance needs. -
Vendor:Dell
Dell T640 | Tower/Rack Convertible Server | 2-socket Intel Xeon Scalable | ECC RDIMM | High-density 2.5"/3.5" bays | GPU-ready options | Redundant hot-plug PSUs | BMC remote management
A highly scalable, rack-convertible 2-socket tower optimized for consolidation and VDI. Offers high drive-bay density, GPU-ready options, and robust PCIe expansion for diverse workloads, with redundant power and advanced remote management. -
Vendor:Lenovo
Lenovo SR860 | 4-socket Xeon Scalable | 4U rack | up to 48 DIMMs / ~6TB RAM | up to 48x 2.5in bays (SAS/SATA/NVMe) | PCIe Gen3 expansion + GPU support | OCP networking | Redundant hot-swap PSUs | XClarity
A high-capacity 4U, 4-socket system designed for mission-critical databases, large virtualization clusters, and analytics. The expansive chassis supports more drive bays and PCIe slots for GPUs/accelerators, high-port-count NICs, and storage controllers. Flexible media options include SAS/SATA and NVMe, while strong RAS, hot-swap redundancy, and XClarity management ensure reliability and control at scale. -
Vendor:Cisco
Cisco UCSB-GPU-P6-F | NVIDIA GRID P6 mezzanine GPU | front slot | vGPU-ready (VDI/3D) | blade-optimized
UCSB-GPU-P6-F
Vendor:CiscoCisco UCSB-GPU-P6-F | NVIDIA GRID P6 mezzanine GPU | front slot | vGPU-ready (VDI/3D) | blade-optimized
Front mezzanine GPU module based on NVIDIA GRID P6 for UCS blade servers, delivering virtualized graphics (vGPU) and GPU acceleration for VDI, 3D/CAD, and mixed workloads. Installs in the front mezzanine slot, optimized for blade thermals and density. Supports NVIDIA vGPU software (license required) for multi-user profiles and secure GPU sharing. -
Vendor:Cisco
Cisco UCS-CPU-A7543 | EPYC 7543 | 32C 2.8GHz (3.7GHz Turbo) | 256MB L3 | 225W | DDR4-3200 | PCIe 4.0 | SP3
UCS-CPU-A7543
Vendor:CiscoCisco UCS-CPU-A7543 | EPYC 7543 | 32C 2.8GHz (3.7GHz Turbo) | 256MB L3 | 225W | DDR4-3200 | PCIe 4.0 | SP3
AMD EPYC 7543 (Milan) balances per-core speed with core count, delivering excellent performance for virtualization, databases, and HPC workloads. With 32 cores, 256MB L3, and PCIe Gen4, it supports dense NVMe, GPUs, and high-speed networking on SP3 platforms. Eight-channel DDR4-3200 ECC memory maximizes bandwidth for memory-heavy applications. -
Vendor:Cisco
Cisco UCSB-GPU-P6-R | NVIDIA GRID P6 mezzanine GPU | rear slot | vGPU-ready (VDI/3D) | blade-optimized
UCSB-GPU-P6-R
Vendor:CiscoCisco UCSB-GPU-P6-R | NVIDIA GRID P6 mezzanine GPU | rear slot | vGPU-ready (VDI/3D) | blade-optimized
Rear mezzanine GPU module based on NVIDIA GRID P6 for UCS blade servers, providing virtualized graphics (vGPU) and GPU acceleration for VDI, 3D/CAD, and visualization workloads. Installs in the rear mezzanine slot, aligned with blade airflow and power envelopes. Supports NVIDIA vGPU software (license required) for secure multi-tenant GPU sharing. -
Vendor:Cisco
Cisco UCSC-885A-M8-H11 | AI training server | 8x H100 GPUs | 8x ConnectX-7 | BlueField-3 DPU | 23TB memory
UCSC-885A-M8-H11
Vendor:CiscoCisco UCSC-885A-M8-H11 | AI training server | 8x H100 GPUs | 8x ConnectX-7 | BlueField-3 DPU | 23TB memory
High-performance rack server configuration built for large-scale AI training and inference. Equipped with 8x NVIDIA H100 GPUs, 8x ConnectX-7 network adapters for high-throughput fabric connectivity, a BlueField-3 DPU for accelerated networking and security offload, and 23TB system memory for massive in-memory datasets. Ideal for LLM training, HPC, and advanced analytics workloads. -
Vendor:Cisco
Cisco UCSC-885A-M8-H12 | AI server | H100 GPUs 8x (B3140H) | BlueField-3 DPU (B3220) | 23TB RAM
UCSC-885A-M8-H12
Vendor:CiscoCisco UCSC-885A-M8-H12 | AI server | H100 GPUs 8x (B3140H) | BlueField-3 DPU (B3220) | 23TB RAM
High-density AI compute platform built for large-scale training and inference, populated with 8x NVIDIA H100 accelerators (B3140H) and a BlueField-3 DPU (B3220) to offload networking/storage datapaths. Delivers 23TB installed memory and integrates with UCS tooling for streamlined deployment and lifecycle management. -
Vendor:Cisco
Cisco UCSC-885A-M8-H20 | AI server | H200 GPUs | 2x ConnectX-7 400G | 15TB RAM
UCSC-885A-M8-H20
Vendor:CiscoCisco UCSC-885A-M8-H20 | AI server | H200 GPUs | 2x ConnectX-7 400G | 15TB RAM
Next-generation AI server featuring NVIDIA H200 accelerators paired with dual ConnectX-7 400G-class adapters for extreme bandwidth and low latency across AI fabrics. With 15TB of installed memory, it’s tuned for large-scale training, fine-tuning, and high-performance inference, and integrates seamlessly with UCS management. -
Vendor:Cisco
Cisco UCSC-885A-M8-H21 | AI server | H200 GPUs | ConnectX-7 400G (high-density) | BlueField-3 DPU (B3220) | 23TB RAM
UCSC-885A-M8-H21
Vendor:CiscoCisco UCSC-885A-M8-H21 | AI server | H200 GPUs | ConnectX-7 400G (high-density) | BlueField-3 DPU (B3220) | 23TB RAM
High-capacity AI platform with NVIDIA H200 accelerators, dense ConnectX-7 400G-class connectivity for clustered training, and a BlueField-3 DPU (B3220) to offload networking, storage, and security services. The system comes with 23TB installed memory and UCS integration for streamlined operations. -
Vendor:Cisco
Cisco UCSC-885A-M8-H13 | AI server | H100 GPUs (high-density) | 2x ConnectX-7 400G | 15TB RAM
UCSC-885A-M8-H13
Vendor:CiscoCisco UCSC-885A-M8-H13 | AI server | H100 GPUs (high-density) | 2x ConnectX-7 400G | 15TB RAM
Enterprise AI compute server configured with NVIDIA H100 accelerators and dual ConnectX-7 400G-class adapters for ultra-fast fabric connectivity. With 15TB installed memory and UCS integration, it’s engineered for model training, fine-tuning, and high-throughput inference in production environments. -
Vendor:Cisco
Cisco UCSC-885A-M8-H26 | Rack server | 8x H200 GPUs | IO: 2x B3220 + CX7 networking | Memory: 23TB
UCSC-885A-M8-H26
Vendor:CiscoCisco UCSC-885A-M8-H26 | Rack server | 8x H200 GPUs | IO: 2x B3220 + CX7 networking | Memory: 23TB
Enterprise AI rack server with 8x NVIDIA H200 GPUs, a blend of BlueField-class DPUs (2x B3220) and ConnectX-7 networking, and 23TB of installed system memory. Built for distributed training, secure accelerated networking, and large model pipelines. -
Vendor:Cisco
Cisco UCSC-885A-M8-H23 | Rack server | 8x H200 GPUs | Networking: ConnectX-7 | Memory: 2.3TB
UCSC-885A-M8-H23
Vendor:CiscoCisco UCSC-885A-M8-H23 | Rack server | 8x H200 GPUs | Networking: ConnectX-7 | Memory: 2.3TB
AI-optimized rack server with 8x NVIDIA H200 GPUs, ConnectX-7 networking, and 2.3TB of installed system memory. Built for multi-GPU training, inference at scale, and accelerated data pipelines in enterprise data centers.
Why Choose XS Network Tech?
We are a trusted partner for businesses of all sizes, including government departments, data centres, and service providers. Our expert team in sales, logistics, and customer service ensures that your needs are met with speed and precision, from pre-sales consultation to order fulfilment. With a commitment to fast delivery, sustainability, and a wide inventory, XS Network Tech is your go-to source for IT hardware. Trust us for quality, fast responses, and a hassle-free experience every time.