-
Vendor:Cisco
Cisco HX-GPU-P40 | Tesla P40 24GB GDDR5, PCIe 3.0 x16, Passive Cooling, 250W TDP
HX-GPU-P40
Vendor:CiscoCisco HX-GPU-P40 | Tesla P40 24GB GDDR5, PCIe 3.0 x16, Passive Cooling, 250W TDP
Datacenter inference and virtualization GPU with 24GB of GDDR5, designed for high-density server deployments. The passive-cooled PCIe form factor relies on chassis airflow, simplifying maintenance and reducing moving parts. Ideal for AI inference, VDI, rendering, and video transcoding where memory capacity and codec acceleration matter. Robust software ecosystem support enables scalable, multi-tenant deployments. -
Vendor:Cisco
Cisco HX-GPU-RTX6000 | RTX 6000 Passive 24GB GDDR6, PCIe 3.0 x16, 250W TGP, Tensor/RT Cores
HX-GPU-RTX6000
Vendor:CiscoCisco HX-GPU-RTX6000 | RTX 6000 Passive 24GB GDDR6, PCIe 3.0 x16, 250W TGP, Tensor/RT Cores
Datacenter-optimized variant of the RTX 6000 with passive cooling for dense rack deployments. 24GB of GDDR6 with ECC supports complex visualization, rendering, AI inference, and mixed workloads. Turing architecture with Tensor and RT Cores accelerates AI features and ray tracing where supported. Designed for server airflow and stable 24/7 operation via PCIe 3.0 x16. -
Vendor:Cisco
Cisco HX-GPU-P100-16G | Tesla P100 16GB HBM2, PCIe 3.0 x16, Passive Cooling, 250W TDP
HX-GPU-P100-16G
Vendor:CiscoCisco HX-GPU-P100-16G | Tesla P100 16GB HBM2, PCIe 3.0 x16, Passive Cooling, 250W TDP
Datacenter-grade accelerator with expanded 16GB HBM2 memory for larger datasets and deeper models. Built for HPC and AI workloads where memory bandwidth, ECC, and sustained compute are critical. The passive, fanless design relies on server chassis airflow, enabling quiet and dense rack deployments. PCIe 3.0 x16 connectivity ensures compatibility across leading enterprise servers. -
Vendor:Cisco
Cisco HX-GPU-RTX8000 | Quadro RTX 8000 | 48GB GDDR6 | Passive Cooling | 250W TGP | PCIe Gen3 x16
HX-GPU-RTX8000
Vendor:CiscoCisco HX-GPU-RTX8000 | Quadro RTX 8000 | 48GB GDDR6 | Passive Cooling | 250W TGP | PCIe Gen3 x16
Data‑center optimized Quadro RTX 8000 with 48GB GDDR6 for high‑end rendering, AI/ML workloads, and GPU virtualization. Passive cooling design requires server‑class airflow; ideal for dense rack deployments. -
Vendor:Cisco
Cisco HX-GPU-V100 | Tesla V100 | 16GB HBM2 | Passive Cooling | 250W TDP | PCIe Gen3 x16
HX-GPU-V100
Vendor:CiscoCisco HX-GPU-V100 | Tesla V100 | 16GB HBM2 | Passive Cooling | 250W TDP | PCIe Gen3 x16
High‑performance accelerator based on the Volta architecture with 16GB HBM2 for AI training, HPC, and advanced analytics. PCIe form factor with passive cooling for enterprise racks. -
Vendor:Cisco
Cisco HX-GPU-T4-16 | T4 | 16GB GDDR6 | Low‑Profile | 75W TDP | PCIe Gen3 x16
HX-GPU-T4-16
Vendor:CiscoCisco HX-GPU-T4-16 | T4 | 16GB GDDR6 | Low‑Profile | 75W TDP | PCIe Gen3 x16
Low‑profile, single‑slot T4 accelerator with 16GB GDDR6 for AI inference, VDI, and video transcoding in density‑optimized servers. Passive design powered by the PCIe slot for efficient deployment. -
Vendor:Cisco
Cisco HX-GPU-V100-32 | Tesla V100 | 32GB HBM2 | Passive Cooling | 250W TDP | PCIe Gen3 x16
HX-GPU-V100-32
Vendor:CiscoCisco HX-GPU-V100-32 | Tesla V100 | 32GB HBM2 | Passive Cooling | 250W TDP | PCIe Gen3 x16
Volta‑based accelerator with expanded 32GB HBM2 for larger models and datasets in AI training and HPC workloads. PCIe passive design tailored for enterprise rack servers. -
Vendor:Cisco
Cisco HX-P-M5D100GF | Dual 100GbE QSFP28 PCIe3 x16 NIC | RoCEv2, NVMe-oF, SR-IOV | Breakout capable
HX-P-M5D100GF
Vendor:CiscoCisco HX-P-M5D100GF | Dual 100GbE QSFP28 PCIe3 x16 NIC | RoCEv2, NVMe-oF, SR-IOV | Breakout capable
High-performance dual-port 100GbE QSFP28 adapter for demanding data center, storage, and HPC workloads. PCIe 3.0 x16 bandwidth paired with RDMA (RoCEv2), NVMe-oF acceleration, and extensive virtualization features ensures exceptional throughput and low latency. Supports breakout to 4x25GbE per port with appropriate cables for flexible topologies. Ideal for leaf/spine fabrics, GPU clusters, and scalable storage. -
Vendor:Cisco
Cisco HX-PSU1-2300W | 2300W AC hot-swap PSU, 80 PLUS Titanium, 100-240V auto-ranging, redundant-ready
HX-PSU1-2300W
Vendor:CiscoCisco HX-PSU1-2300W | 2300W AC hot-swap PSU, 80 PLUS Titanium, 100-240V auto-ranging, redundant-ready
Ultra-high-capacity 2300W AC power module for UCS rack servers, engineered for maximum efficiency and performance headroom. Titanium-grade efficiency reduces thermal load while hot-swap design supports rapid replacement and continuous uptime. Ideal for high-core CPUs, dense memory, and GPU-accelerated builds. -
Vendor:HPE
HPE P14608-B21 | DL38X Gen10 Plus | Maximum performance hot-plug fan kit | N+1 cooling readiness | high-TDP/NVMe configs
Upgrade cooling capacity on DL380/DL385 Gen10 Plus servers for demanding configurations. This maximum performance fan kit delivers higher airflow and supports redundant cooling for improved uptime. Recommended for high-TDP processors, dense NVMe storage, and accelerator/GPU options as defined by platform thermal guidelines. Installs tool-less into the fan bank and integrates with system thermal management. -
Vendor:HPE
HPE P69872-B21 | DL385 Gen11 GPU/Storage Battery Bracket Kit, Mounting Hardware
P69872-B21
Vendor:HPEHPE P69872-B21 | DL385 Gen11 GPU/Storage Battery Bracket Kit, Mounting Hardware
Mounting solution for installing a controller or accelerator battery in ProLiant DL385 Gen11 systems, ensuring secure placement and cable routing within the chassis. Ideal when adding RAID cache batteries or GPU-related storage modules. -
Vendor:HPE
HPE R8T26C | GPU accelerator | NVIDIA A16 | 64GB GDDR6 | PCIe Gen4 x16 | passive dual‑slot FHFL | VDI/vGPU optimized
High‑density, multi‑GPU data center accelerator designed for VDI and virtual GPU workloads. The NVIDIA A16 integrates four GPUs with a total of 64GB GDDR6, delivering excellent user density and smooth graphics for virtual desktops and applications. Passive, dual‑slot FHFL design for server airflow environments; ideal for consolidation and secure multi‑tenancy. -
Vendor:Dell
Dell R740 | 2U dual-socket Xeon Scalable | up to 24 DIMMs | up to 16x 2.5in or 8x 3.5in bays | up to 3x double‑width GPUs | iDRAC9 management
Versatile 2U enterprise server optimized for virtualization, databases, and VDI—balancing compute, storage, and accelerator options. Scales with dual Xeon Scalable CPUs, 24 DIMMs, flexible drive configurations, and iDRAC9 for secure, automated management. -
Vendor:Dell
Dell R760XA | 2U GPU-optimized | 2x Intel Xeon Scalable Gen4 | DDR5 | PCIe 5.0 | OCP 3.0 | iDRAC9 | NVMe/SAS/SATA
Accelerator-optimized 2U platform engineered for AI/ML inference, VDI, and high-density compute. Flexible storage with NVMe/SAS/SATA options, PCIe 5.0 expansion, and OCP 3.0 networking provide balanced bandwidth for GPUs and fast I/O. -
Vendor:Dell
Dell R940xa | 4-socket GPU-optimized rack server, DDR4, multi-GPU support, NVMe storage options, PCIe 3.0, iDRAC9
A 4-socket, accelerator-ready platform designed for AI/ML, HPC, and data-intensive analytics. Balanced PCIe topology, generous memory capacity, and high NVMe throughput enable demanding GPU-accelerated workloads. -
Vendor:Lenovo
Lenovo SR655 | 2U rack | single AMD EPYC 7002/7003 | up to 64 cores | DDR4-3200 up to 16 DIMMs | PCIe 4.0 | flexible 2.5"/3.5" bays incl. NVMe | OCP 3.0 NIC | redundant 80 PLUS PSUs | XClarity management
Single-socket performance platform optimized for price/performance, storage I/O, and GPU options. AMD EPYC Rome/Milan CPUs, PCIe 4.0 lanes, and dense drive configurations suit virtualization, SDS, and edge-to-core workloads.
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.