-
Vendor:Cisco
Cisco CAI-NVL2-H200 | NVLink 2-Way Bridge | Compatible with NVIDIA H200 | GPU Interconnect
CAI-NVL2-H200
Vendor:CiscoCisco CAI-NVL2-H200 | NVLink 2-Way Bridge | Compatible with NVIDIA H200 | GPU Interconnect
A 2-way NVLink bridge for linking two NVIDIA H200 GPUs, delivering high-bandwidth, low-latency peer-to-peer communication for accelerated AI/ML and HPC workloads. Confirm GPU model and chassis spacing compatibility prior to purchase. -
Vendor:Cisco
Cisco CAI-NVL2-H100 | NVLink 2-Way Bridge | Compatible with NVIDIA H100 | GPU Interconnect
CAI-NVL2-H100
Vendor:CiscoCisco CAI-NVL2-H100 | NVLink 2-Way Bridge | Compatible with NVIDIA H100 | GPU Interconnect
A 2-way NVLink bridge enabling high-bandwidth, low-latency interconnect between two NVIDIA H100 GPUs for accelerated multi-GPU performance in AI/ML and HPC workloads. Verify card and chassis spacing compatibility before purchase. -
Vendor:Cisco
Cisco CAI-INF4-MI210 | GPU interconnect bridges | 4-way MI210 | Infinity Fabric link mesh
CAI-INF4-MI210
Vendor:CiscoCisco CAI-INF4-MI210 | GPU interconnect bridges | 4-way MI210 | Infinity Fabric link mesh
4-way Infinity bridge set for MI210 GPUs, enabling a multi-GPU fabric for high-bandwidth, low-latency peer-to-peer communication across four cards. Built for scalable HPC/AI workloads requiring efficient inter-GPU data exchange. -
Vendor:Cisco
Cisco CAI-INF2-MI210 | GPU interconnect bridge | 2-way MI210 | Infinity Fabric link | low-latency P2P
CAI-INF2-MI210
Vendor:CiscoCisco CAI-INF2-MI210 | GPU interconnect bridge | 2-way MI210 | Infinity Fabric link | low-latency P2P
2-way Infinity bridge for interconnecting a pair of MI210 GPUs, enabling high-bandwidth, low-latency peer-to-peer communication for HPC and AI workloads. Ideal for multi-GPU servers that require direct GPU-to-GPU data exchange without traversing the host. -
Vendor:Cisco
Cisco CAI-GPU-RTXP6000 | RTX Pro 6000 GPU — 96GB, 600W, 2-slot FHFL, PCIe, NVLink-capable
CAI-GPU-RTXP6000
Vendor:CiscoCisco CAI-GPU-RTXP6000 | RTX Pro 6000 GPU — 96GB, 600W, 2-slot FHFL, PCIe, NVLink-capable
High-performance professional GPU kit for C845A platforms, delivering 96GB of graphics memory and a 2-slot full-height, full-length PCIe form factor. Designed for AI inference, visualization, and compute-heavy workloads with support for NVLink-paired configurations where applicable. Integrates cleanly into server workflows requiring deterministic performance and high memory capacity. -
Vendor:Cisco
Cisco CAI-GPU-MI210 | Instinct MI210 | 64GB HBM2e ECC | 300W TDP | 2-slot FHFL | PCIe 4.0 x16 | Passive
CAI-GPU-MI210
Vendor:CiscoCisco CAI-GPU-MI210 | Instinct MI210 | 64GB HBM2e ECC | 300W TDP | 2-slot FHFL | PCIe 4.0 x16 | Passive
Data center compute accelerator built on CDNA2 for HPC and AI workloads. Delivers 64GB HBM2e with ECC in a 2-slot FHFL, passively cooled PCIe 4.0 x16 form factor for qualified servers. Suitable for double-precision HPC, simulation, and AI acceleration. -
Vendor:Cisco
Cisco CAI-GPU-L40S | L40S | 48GB GDDR6 ECC | 350W TDP | 2-slot FHFL | PCIe 4.0 x16 | Passive
CAI-GPU-L40S
Vendor:CiscoCisco CAI-GPU-L40S | L40S | 48GB GDDR6 ECC | 350W TDP | 2-slot FHFL | PCIe 4.0 x16 | Passive
Versatile data center PCIe accelerator optimized for AI inference, graphics rendering, and media processing. Features 48GB GDDR6 with ECC in a 2-slot FHFL, passively cooled design for OEM servers. Ideal for mixed AI/graphics pipelines and high-density deployments. -
Vendor:Cisco
Cisco CAI-GPU-H200-NVL | H200 NVL | 141GB HBM3e ECC | 600W TDP | 2-slot FHFL | Passive | PCIe x16
CAI-GPU-H200-NVL
Vendor:CiscoCisco CAI-GPU-H200-NVL | H200 NVL | 141GB HBM3e ECC | 600W TDP | 2-slot FHFL | Passive | PCIe x16
High-capacity data center accelerator tailored for large-language-model inference/training, combining 141GB HBM3e with ECC and a passively cooled 2-slot FHFL form factor. NVL design supports high-bandwidth multi-GPU scaling in qualified servers. Confirm chassis airflow and power delivery before deployment. -
Vendor:Cisco
Cisco CAI-GPU-H100-NVL | H100 NVL | 94GB HBM3 ECC | 400W TDP | 2-slot FHFL | Passive | PCIe x16
CAI-GPU-H100-NVL
Vendor:CiscoCisco CAI-GPU-H100-NVL | H100 NVL | 94GB HBM3 ECC | 400W TDP | 2-slot FHFL | Passive | PCIe x16
Data center PCIe accelerator for large-scale AI inference and training, featuring 94GB HBM3 with ECC in a 2-slot FHFL, passively cooled form factor designed for OEM servers. NVL variant enables high-throughput interconnect for multi-GPU deployments. Ensure adequate chassis airflow and power headroom. -
Vendor:Cisco
Cisco CAI-BRK-GPU | C845A GPU accessory kit | PCIe GPU power cabling + retention hardware | supports NVIDIA/AMD accelerators
Accessory set for enabling PCIe GPU deployments in the C845A platform, bundling auxiliary power harnessing and mounting/retention elements required by supported accelerators. Streamlines installation while maintaining airflow and cable management inside the chassis. Ideal when adding or upgrading GPU capacity on an existing system. -
Vendor:Cisco
Cisco C885A-M8-MI3X-SLD | C885A M8 GPU sled | MI300X OAM support (P/N 100-300000069H) | AI accelerator integration
C885A-M8-MI3X-SLD
Vendor:CiscoCisco C885A-M8-MI3X-SLD | C885A M8 GPU sled | MI300X OAM support (P/N 100-300000069H) | AI accelerator integration
High-density GPU accelerator sled for the C885A M8 designed to host MI300X OAM modules (including P/N 100-300000069H), enabling scalable AI and HPC performance with chassis-level power and airflow alignment. -
Vendor:Cisco
Cisco C885A-M8-MI35-SLD | C885A M8 GPU sled | MI350X OAM support | AI/HPC accelerator expansion
C885A-M8-MI35-SLD
Vendor:CiscoCisco C885A-M8-MI35-SLD | C885A M8 GPU sled | MI350X OAM support | AI/HPC accelerator expansion
GPU accelerator sled engineered for the C885A M8 platform to host MI350X-class OAM accelerators, adding high-density AI/HPC compute capability while maintaining optimized chassis power and airflow integration. -
Vendor:NVIDIA
NVIDIA 900-5G195-2551-000 | RTX Pro 2000 Blackwell | 16GB GDDR7, PCIe 5.0 x8, 70W, 4x miniDP 2.1, 2-slot
900-5G195-2551-000
In stock
Vendor:NVIDIANVIDIA 900-5G195-2551-000 | RTX Pro 2000 Blackwell | 16GB GDDR7, PCIe 5.0 x8, 70W, 4x miniDP 2.1, 2-slot
Efficient Blackwell-based pro GPU balancing performance and power with 16GB GDDR7 and PCIe 5.0 x8 connectivity. Four miniDP 2.1 outputs support multi-4K or single 8K workflows in compact systems. -
Vendor:NVIDIA
NVIDIA 900-5G195-2501-000 | RTX Pro 4000 SFF Blackwell | 24GB GDDR7, PCIe 5.0 x16, 140W, 4x DP 2.1, SFF 1-slot
900-5G195-2501-000
Vendor:NVIDIANVIDIA 900-5G195-2501-000 | RTX Pro 4000 SFF Blackwell | 24GB GDDR7, PCIe 5.0 x16, 140W, 4x DP 2.1, SFF 1-slot
Next-gen Blackwell workstation GPU delivering higher throughput with 24GB GDDR7 and PCIe 5.0, engineered for dense SFF builds. Four full-size DP 2.1 ports enable advanced high-resolution, high-refresh workflows for visualization and content creation. -
Vendor:NVIDIA
NVIDIA 900-5G192-2571-000 | RTX 4000 SFF Ada | 20GB GDDR6, 160-bit 280 GB/s, PCIe 4.0 x16, 4x miniDP, SFF 2-slot
900-5G192-2571-000
Vendor:NVIDIANVIDIA 900-5G192-2571-000 | RTX 4000 SFF Ada | 20GB GDDR6, 160-bit 280 GB/s, PCIe 4.0 x16, 4x miniDP, SFF 2-slot
Small form factor pro GPU with 20GB GDDR6 and Ada acceleration to speed CAD, DCC, visualization, and AI-assisted workflows. Four miniDP outputs and ample memory bandwidth deliver smooth, multi-display productivity in compact workstations. -
Vendor:NVIDIA
NVIDIA 900-5G192-2541-000 | RTX 2000 Ada | 16GB GDDR6, PCIe 4.0 x16, 4x miniDP 1.4a, up to 4 displays
900-5G192-2541-000
Vendor:NVIDIANVIDIA 900-5G192-2541-000 | RTX 2000 Ada | 16GB GDDR6, PCIe 4.0 x16, 4x miniDP 1.4a, up to 4 displays
Compact professional GPU for CAD/DCC and visualization workloads, built on Ada architecture with 16GB GDDR6 for large models and smooth multi-monitor productivity. Four mini DisplayPort outputs with DSC enable high-resolution, color-accurate workflows across up to four displays.
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.