-
Vendor:Cisco
Cisco UCSX-GPU-A40-D | A40 Data Center GPU | PCIe Gen4 x16 | 48GB GDDR6 ECC | 300W | Passive | Compute/graphics/AI | Includes power cable
Versatile data center GPU for compute, graphics virtualization, and AI inference, featuring 48GB GDDR6 ECC on a PCIe Gen4 x16 interface with a 300W passive thermal design for rack servers. Ideal for rendering, visualization, and vGPU deployments (vGPU licensing required for virtualization features). Includes required power cable. -
Vendor:Cisco
Cisco UCSX-GPU-A40 | A40 Data Center GPU | PCIe Gen4 x16 | 48GB GDDR6 ECC | 300W | Passive | Compute/graphics/AI | Includes power cable
Versatile data center GPU for compute, graphics virtualization, and AI inference, featuring 48GB GDDR6 ECC on a PCIe Gen4 x16 interface with a 300W passive thermal design for rack servers. Ideal for rendering, visualization, and vGPU deployments (vGPU licensing required for virtualization features). Includes required power cable. -
Vendor:Cisco
Cisco UCSX-GPU-A16-D | A16 GPU | PCIe Gen4 x16 | 4x16GB GDDR6 (64GB total) | 250W | Passive, server-optimized | VDI density | Includes power cable
High-density VDI accelerator for rack servers, delivering 64GB GDDR6 via four GPU partitions on a PCIe Gen4 x16 card with a 250W passive, server-optimized thermal design. Ideal for virtual desktops, app streaming, and graphics virtualization (vGPU licensing required for virtualization features). Includes required power cable. -
Vendor:Cisco
Cisco UCSX-GPU-A16 | VDI GPU, 64GB GDDR6, PCIe Gen4 x16, passive, vGPU-ready
UCSX-GPU-A16
Vendor:CiscoCisco UCSX-GPU-A16 | VDI GPU, 64GB GDDR6, PCIe Gen4 x16, passive, vGPU-ready
Data center GPU optimized for virtual desktops and application virtualization. Delivers high user density with 64GB GDDR6, passive cooling for server airflow, and PCIe Gen4 x16 connectivity. Supports NVIDIA vGPU software to allocate profiles per VM for graphics-accelerated VDI and Windows/Linux applications. -
Vendor:Cisco
Cisco UCSX-GPU-A100-80 | Tensor Core GPU, 80GB HBM2e, PCIe Gen4 x16, passive 300W, incl. power cable
UCSX-GPU-A100-80
Vendor:CiscoCisco UCSX-GPU-A100-80 | Tensor Core GPU, 80GB HBM2e, PCIe Gen4 x16, passive 300W, incl. power cable
Data center Tensor Core GPU module with 80GB HBM2e for AI training, inference, data analytics, and HPC acceleration in UCS servers. Passive-cooled, PCIe Gen4 x16 form factor with auxiliary power cable, supporting CUDA and mixed-precision acceleration with enterprise vGPU options for partitioning and multi-tenant workflows. -
Vendor:Cisco
Cisco UCSC-GPUV100SXM32 | GPU accelerator | 32GB HBM2, SXM2 300W | NVLink 2.0 | Tensor/FP16/FP32 compute
UCSC-GPUV100SXM32
Vendor:CiscoCisco UCSC-GPUV100SXM32 | GPU accelerator | 32GB HBM2, SXM2 300W | NVLink 2.0 | Tensor/FP16/FP32 compute
High-density SXM2 GPU accelerator with 32GB ECC HBM2 for AI/ML, HPC, and data analytics. NVLink 2.0 interconnect enables low-latency, high-bandwidth multi-GPU scaling in compatible servers. SXM2 form factor integrates with server baseboards for optimal power and cooling; not a standalone PCIe card. Supports modern accelerated computing frameworks and mixed-precision workloads. -
Vendor:Cisco
Cisco UCSC-GPUA100-80-D | A100 PCIe | 80GB HBM2e | 300W passive | PCIe 4.0 x16 | Tensor Core data center GPU
UCSC-GPUA100-80-D
Vendor:CiscoCisco UCSC-GPUA100-80-D | A100 PCIe | 80GB HBM2e | 300W passive | PCIe 4.0 x16 | Tensor Core data center GPU
Ampere-based accelerator with 80GB HBM2e for state-of-the-art AI training, inference, and HPC. The passive, dual-slot PCIe 4.0 card supports multi-precision Tensor Cores and MIG to partition GPU resources for consolidated workloads. Confirm slot, power, and airflow requirements per your server’s qualification guide. -
Vendor:Cisco
Cisco UCSC-GPU-VGXK10 | GRID K10 PCIe | 8GB GDDR5 (4GB x2) | Dual-GPU | PCIe x16 | Passive, dual-slot
UCSC-GPU-VGXK10
Vendor:CiscoCisco UCSC-GPU-VGXK10 | GRID K10 PCIe | 8GB GDDR5 (4GB x2) | Dual-GPU | PCIe x16 | Passive, dual-slot
Kepler-generation dual-GPU board designed for legacy virtualization and graphics acceleration use cases. Provides 8GB GDDR5 (4GB per GPU die) on a passive, dual-slot PCIe card for supported data center servers. Ideal for older VDI stacks and applications requiring compatibility with historical GRID software releases. -
Vendor:Cisco
Cisco UCSC-GPU-V100-32 | Tesla V100 PCIe | 32GB HBM2 | 250W passive | PCIe 3.0 x16 | Dual-slot data center GPU
UCSC-GPU-V100-32
Vendor:CiscoCisco UCSC-GPU-V100-32 | Tesla V100 PCIe | 32GB HBM2 | 250W passive | PCIe 3.0 x16 | Dual-slot data center GPU
Volta-based accelerator with expanded 32GB HBM2 for larger AI/HPC models and datasets. The passive, dual-slot PCIe card is designed for enterprise servers, offering tensor cores, ECC memory, and support for virtualization stacks. Validate power, slot, and airflow requirements on your server’s GPU support matrix. -
Vendor:Cisco
Cisco UCSC-GPU-V100 | Tesla V100 PCIe | 16GB HBM2 | 250W passive | PCIe 3.0 x16 | Dual-slot data center GPU
UCSC-GPU-V100
Vendor:CiscoCisco UCSC-GPU-V100 | Tesla V100 PCIe | 16GB HBM2 | 250W passive | PCIe 3.0 x16 | Dual-slot data center GPU
Volta-based data center accelerator for AI, HPC, and analytics workloads. The PCIe add-in card uses a passive heatsink for server chassis airflow, delivers tensor core acceleration, ECC-protected HBM2 memory, and enterprise driver/vGPU software support for virtualized environments. Validate power, space, and airflow against your server’s GPU support matrix. -
Vendor:Cisco
Cisco UCSC-GPU-T4-16 | Tesla T4 | PCIe 3.0 x16 low-profile | 16GB GDDR6 | 75W TDP | Passive-cooled | Single-slot | vGPU-ready
Low-profile, single-slot data center GPU tailored for inference, video processing, and virtualization. 16GB GDDR6 with ECC in a 75W TDP enables high density and efficiency. PCIe 3.0 x16; passive-cooled design relies on server airflow. Ideal for scale-out deployments and vGPU use cases (license required). -
Vendor:Cisco
Cisco UCSC-GPU-RTX8000 | Quadro RTX 8000 Passive | PCIe 3.0 x16 | 48GB GDDR6 | 250W TGP | NVLink support | ECC | vGPU-ready
UCSC-GPU-RTX8000
Vendor:CiscoCisco UCSC-GPU-RTX8000 | Quadro RTX 8000 Passive | PCIe 3.0 x16 | 48GB GDDR6 | 250W TGP | NVLink support | ECC | vGPU-ready
High-memory, passive-cooled Turing GPU for large-scale rendering, simulation, and AI. 48GB GDDR6 with ECC handles massive datasets; optional NVLink enables multi-GPU memory pooling for even larger workloads. PCIe 3.0 x16, 250W, full-height dual-slot; requires strong front-to-back server airflow. Ideal for virtualized and bare-metal deployments; vGPU support available (license required). -
Vendor:Cisco
Cisco UCSC-GPU-RTX6000 | Quadro RTX 6000 Passive | PCIe 3.0 x16 | 24GB GDDR6 | 250W TGP | NVLink support | ECC | vGPU-ready
UCSC-GPU-RTX6000
Vendor:CiscoCisco UCSC-GPU-RTX6000 | Quadro RTX 6000 Passive | PCIe 3.0 x16 | 24GB GDDR6 | 250W TGP | NVLink support | ECC | vGPU-ready
Server-grade, passive-cooled Turing GPU for advanced visualization, rendering, and AI. 24GB GDDR6 with ECC delivers reliable performance at scale; optional NVLink enables high-bandwidth multi-GPU configurations. PCIe 3.0 x16, 250W, full-height dual-slot; requires robust server airflow. Supports CUDA, Tensor, and RT cores; ideal for vGPU environments (license required). -
Vendor:Cisco
Cisco UCSC-GPU-P40 | Tesla P40 | PCIe 3.0 x16 | 24GB GDDR5 | 250W TDP | Passive-cooled | ECC | vGPU-ready
UCSC-GPU-P40
Vendor:CiscoCisco UCSC-GPU-P40 | Tesla P40 | PCIe 3.0 x16 | 24GB GDDR5 | 250W TDP | Passive-cooled | ECC | vGPU-ready
Passive-cooled data center GPU engineered for high-density servers. 24GB GDDR5 with ECC supports large models and reliable compute. PCIe 3.0 x16, 250W, full-height dual-slot; requires front-to-back server airflow. Ideal for AI inference, HPC acceleration, and GPU virtualization (license required). -
Vendor:Cisco
Cisco UCSC-GPU-MI210 | GPU | Instinct MI210 | 64GB HBM2e ECC | PCIe 4.0 x16 | 300W TDP | 2-slot FHFL passive | HPC/AI
Compute-focused accelerator for HPC and AI workloads, combining high-bandwidth 64GB HBM2e ECC memory with PCIe 4.0 x16 connectivity. The Instinct MI210’s dual-slot FHFL passive form factor is tuned for scale-out servers running scientific computing, AI training/inference, and data analytics via the ROCm ecosystem. -
Vendor:Cisco
Cisco UCSC-GPU-M60 | GPU | Tesla M60 | 16GB GDDR5 | PCIe 3.0 x16 | 300W TDP | 2-slot FHFL passive | VDI/graphics
Dual-GPU accelerator targeting graphics-rich VDI, rendering, and virtual workstations. Tesla M60 features 16GB GDDR5 total with a dual-slot FHFL passive design for enterprise servers, delivering strong per-user graphics performance.
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.