649 Search Results for "nvidia connectx-6"
-
Vendor:NVIDIA
NVIDIA 920-9B210-00FN-0M0 | Quantum-2 QM9700 64-Port NDR InfiniBand Switch, 51.2Tbps
920-9B210-00FN-0M0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9B210-00FN-0M0 | Quantum-2 QM9700 64-Port NDR InfiniBand Switch, 51.2Tbps
The NVIDIA Quantum-2 QM9700 is a high-performance InfiniBand switch engineered for AI training clusters, HPC environments, and hyperscale data centers. Delivering 64 ports of NDR 400Gb/s connectivity via 32 OSFP connectors in a compact 1U chassis, it achieves 51.2 Tbps aggregate bidirectional throughput with sub-100ns port-to-port latency. Ideal for NVIDIA DGX SuperPOD deployments and large-scale GPU compute fabrics requiring ultra-low latency RDMA, adaptive routing, and in-network computing acceleration. -
Vendor:NVIDIA
NVIDIA 920-9B210-00RN-0M6 | Quantum‑2 NDR InfiniBand switch | 64x 400G NDR over 32x OSFP | Non‑PoE | 48V DC input
920-9B210-00RN-0M6
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9B210-00RN-0M6 | Quantum‑2 NDR InfiniBand switch | 64x 400G NDR over 32x OSFP | Non‑PoE | 48V DC input
Quantum‑2 based NDR InfiniBand fabric switch engineered for large‑scale AI/HPC clusters. Presents 64 NDR ports via 32 OSFP cages for high‑radix, low‑latency connectivity and lossless RDMA transport. Ideal for DGX/SuperPOD leaf/spine roles with advanced congestion control and in‑band telemetry. -
Vendor:NVIDIA
NVIDIA 920-9B110-00RH-0M0 | 40x QSFP56 200Gb HDR IB | 2x PSU | C2P airflow | Rail kit | Managed (x86 CPU)
920-9B110-00RH-0M0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9B110-00RH-0M0 | 40x QSFP56 200Gb HDR IB | 2x PSU | C2P airflow | Rail kit | Managed (x86 CPU)
High‑performance 1U HDR InfiniBand switch with embedded x86 CPU for on‑box fabric management. Ideal for AI/HPC clusters requiring non‑blocking 200Gb/s per port, ultra‑low latency, adaptive routing, and SHARP‑class in‑network acceleration. This configuration provides C2P airflow, dual hot‑swap PSUs, and includes rack rails. -
Vendor:NVIDIA
NVIDIA 920-9B020-00FA-0D2 | 8x IB + 8x Ethernet ports | 2U IB↔Ethernet gateway | line‑rate bridging
920-9B020-00FA-0D2
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9B020-00FA-0D2 | 8x IB + 8x Ethernet ports | 2U IB↔Ethernet gateway | line‑rate bridging
Purpose-built gateway appliance to bridge InfiniBand fabrics with Ethernet networks for storage, services, and external connectivity. Delivers line‑rate translation with consistent latency and simple operations, enabling mixed‑fabric data centers to scale without re‑architecting core networks. -
Vendor:NVIDIA
NVIDIA 930-9XBRK-00MF-000 | HHHL Bracket Kit for BlueField-2 DPU, 10-Pack, 2x SFP56
930-9XBRK-00MF-000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 930-9XBRK-00MF-000 | HHHL Bracket Kit for BlueField-2 DPU, 10-Pack, 2x SFP56
Replacement HHHL bracket kit designed for NVIDIA BlueField-2 DPU cards with dual SFP56 ports. This 10-pack includes half-height half-length brackets with precise cutouts for 2x SFP56 network connectors, ensuring proper fit and airflow for compatible BlueField-2 models BF2M322A, BF2M332A, and BF2H322A in standard server chassis installations. -
Vendor:Cisco
Cisco HCIX-GPU-A16 | NVIDIA A16 GPU, Quad-GPU, 64GB GDDR6, 250W Passive
HCIX-GPU-A16
Stock Status: Enquire
Vendor:CiscoCisco HCIX-GPU-A16 | NVIDIA A16 GPU, Quad-GPU, 64GB GDDR6, 250W Passive
The Cisco HCIX-GPU-A16 is a purpose-built virtual desktop infrastructure accelerator featuring four independent NVIDIA Ampere architecture GPUs on a single dual-slot PCIe 4.0 card. With 64GB total GDDR6 memory across four 16GB GPUs, it delivers exceptional user density for graphics-rich VDI deployments, supporting up to 64 concurrent virtual desktop sessions per card. The 250W passive cooling design integrates seamlessly into Cisco UCS and HyperFlex hyperconverged infrastructure platforms. -
Vendor:NVIDIA
NVIDIA 980-9I30L-00N000 | 800G OSFP twin-port 2x400G FR4 | 2x NDR, 1310nm SMF, 2km, dual LC duplex
980-9I30L-00N000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I30L-00N000 | 800G OSFP twin-port 2x400G FR4 | 2x NDR, 1310nm SMF, 2km, dual LC duplex
Twin‑port 800G OSFP transceiver providing two independent long‑reach 400G links: 400GbE FR4 or InfiniBand NDR over duplex SMF up to 2 km. Ideal for aggregation and long‑reach leaf/spine connections without breakout harnesses. -
Vendor:NVIDIA
NVIDIA 900-5G147-2550-000 | RTX PRO 4500 32GB GDDR7 Graphics Card, 200W, Dual-Slot
900-5G147-2550-000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-5G147-2550-000 | RTX PRO 4500 32GB GDDR7 Graphics Card, 200W, Dual-Slot
The NVIDIA RTX PRO 4500 Blackwell is a professional workstation graphics card engineered for demanding AI, rendering, and design workflows. Built on the Blackwell architecture with 32GB of GDDR7 ECC memory and 896 GB/s bandwidth, it accelerates complex 3D modeling, generative AI applications, ray tracing, and neural rendering. Featuring 10,496 CUDA cores, 328 fifth-generation Tensor Cores, and 82 fourth-generation RT Cores, this dual-slot card delivers exceptional performance for engineering simulations, data science, content creation, and large-scale visualization projects. -
Vendor:NVIDIA
NVIDIA 920-9N42C-00FB-7C0 | Spectrum-4 64-Port 400G Switch, 25.6Tb/s, 2x 25G
920-9N42C-00FB-7C0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9N42C-00FB-7C0 | Spectrum-4 64-Port 400G Switch, 25.6Tb/s, 2x 25G
The NVIDIA MSN5400 Spectrum-4 switch delivers 64 ports of 400GbE in a dense 2U form factor, ideal for hyperscale data center fabrics, AI infrastructure, and high-performance computing deployments. Built on the Spectrum-4 ASIC, it offers 25.6 Tbps throughput and 33.3 Bpps wire-speed forwarding with low cut-through latency. This model includes Cumulus Linux authentication, dual AC power supplies, and power-to-connector airflow for efficient cooling. -
Vendor:Cisco
Cisco HX-GPU-A10 | NVIDIA A10 GPU, 24GB GDDR6 ECC, 9216 CUDA Cores, 150W
HX-GPU-A10
Stock Status: Enquire
Vendor:CiscoCisco HX-GPU-A10 | NVIDIA A10 GPU, 24GB GDDR6 ECC, 9216 CUDA Cores, 150W
The Cisco HX-GPU-A10 is an NVIDIA A10 Tensor Core GPU designed for enterprise AI inference, virtual workstations, and data center graphics workloads. Built on the Ampere architecture with 9,216 CUDA cores, 72 RT cores, and 24GB of GDDR6 ECC memory, it delivers versatile acceleration for rendering, AI compute, and VDI in a single-slot, passively-cooled form factor. Ideal for Cisco HyperFlex HX240c and HX220c M6 server platforms, the A10 combines mainstream GPU performance with data center efficiency at 150W TDP. -
Vendor:NVIDIA
NVIDIA 900-5G147-2570-000 | RTX PRO 4000 Blackwell 24GB GDDR7 Graphics Card
900-5G147-2570-000
In stock
Vendor:NVIDIANVIDIA 900-5G147-2570-000 | RTX PRO 4000 Blackwell 24GB GDDR7 Graphics Card
The NVIDIA RTX PRO 4000 Blackwell is a professional workstation graphics card built on the revolutionary Blackwell architecture. Featuring 24GB of ultra-fast GDDR7 ECC memory with 672GB/s bandwidth and 8,960 CUDA cores, it delivers breakthrough AI performance, neural rendering, and power efficiency in a single-slot design. Ideal for demanding CAD, visualization, AI development, and content creation workflows requiring photorealistic ray tracing and accelerated generative AI capabilities. -
Vendor:NVIDIA
NVIDIA 920-9N302-00FA-0C0 | 64x 200GbE QSFP56, 2U, Linux NOS, Breakout 2x100/4x50 per port, P2C airflow
920-9N302-00FA-0C0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9N302-00FA-0C0 | 64x 200GbE QSFP56, 2U, Linux NOS, Breakout 2x100/4x50 per port, P2C airflow
Ultra‑dense 2U 200GbE switch featuring 64 QSFP56 ports for large-scale leaf/spine cores. Each port supports breakout to 2x100GbE or 4x50GbE, delivering exceptional flexibility for aggregation and server connectivity. The Linux-based NOS enables line-rate L2/L3 forwarding, EVPN-VXLAN overlays, and comprehensive telemetry. Redundant, hot-swappable fans and PSUs with P2C airflow support continuous, serviceable operation in demanding environments. -
Vendor:NVIDIA
NVIDIA 900-5G144-2200-000 | RTX PRO 6000 Graphics Card, 96GB GDDR7 ECC, 24064 CUDA
900-5G144-2200-000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-5G144-2200-000 | RTX PRO 6000 Graphics Card, 96GB GDDR7 ECC, 24064 CUDA
The NVIDIA RTX PRO 6000 Blackwell Workstation Edition is a professional graphics card built on NVIDIA Blackwell architecture, featuring 96GB GDDR7 ECC memory and 24,064 CUDA cores. Designed for AI development, scientific computing, 3D rendering, and real-time simulation, it delivers 125 TFLOPS single precision performance and 380 TFLOPS RT core performance. With fifth-generation Tensor Cores, fourth-generation RT Cores, and PCIe 5.0 x16 interface, this dual-slot GPU accelerates demanding professional workloads including large language model inference, photorealistic rendering, and data science applications. -
Vendor:NVIDIA
NVIDIA 920-9B110-00FH-0MD | 40x QSFP56 200Gb HDR IB | 2x PSU | P2C airflow | Rail kit | Managed (x86 CPU)
920-9B110-00FH-0MD
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9B110-00FH-0MD | 40x QSFP56 200Gb HDR IB | 2x PSU | P2C airflow | Rail kit | Managed (x86 CPU)
Enterprise‑class 1U 200Gb/s HDR InfiniBand switch for AI/HPC fabrics with embedded x86 CPU for on‑switch management. Provides non‑blocking throughput, ultra‑low latency, adaptive routing, and SHARP‑class in‑network acceleration to reduce job completion times. This model features P2C airflow, dual hot‑swap PSUs, and an included rail kit. -
Vendor:NVIDIA
NVIDIA 900-2G179-0020-101-NQR | A2 Tensor Core GPU, 16GB GDDR6, PCIe 4.0 x8, 40-60W
900-2G179-0020-101-NQR
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-2G179-0020-101-NQR | A2 Tensor Core GPU, 16GB GDDR6, PCIe 4.0 x8, 40-60W
The NVIDIA A2 Tensor Core GPU delivers entry-level AI inference acceleration in a compact, low-power design ideal for edge computing and intelligent video analytics deployments. Built on Ampere architecture with 16GB GDDR6 memory and 1280 CUDA cores, this single-slot, low-profile PCIe Gen4 x8 GPU provides up to 4.5 TFLOPS FP32 performance while operating within a configurable 40-60W thermal envelope. Passive cooling and NEBS-3 capability make it well-suited for challenging server environments requiring reliable AI acceleration at scale. -
Vendor:NVIDIA
NVIDIA 980-9I96D-00H010 | 200G QSFP56 to 2x100G QSFP56 | 10m AOC | 850nm MMF | InfiniBand HDR-to-HDR100
980-9I96D-00H010
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I96D-00H010 | 200G QSFP56 to 2x100G QSFP56 | 10m AOC | 850nm MMF | InfiniBand HDR-to-HDR100
Active optical breakout cable enabling one 200G QSFP56 HDR port to fan out into two 100G HDR100 QSFP56 links. Optimized for medium-reach 10 m interconnects, it integrates optics and fiber for simplified deployment, low weight, and consistent high-speed performance. -
Vendor:NVIDIA
NVIDIA 980-9I16Y-00W000 | 400GbE | QSFP-DD | 400GBASE-DR4 | 1310 nm | 500 m SMF | MPO-12/APC
980-9I16Y-00W000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I16Y-00W000 | 400GbE | QSFP-DD | 400GBASE-DR4 | 1310 nm | 500 m SMF | MPO-12/APC
Standards-based 400G DR4 module for spine/leaf uplinks and backbone aggregation. QSFP-DD form factor with parallel single-mode at 1310 nm delivers 500 m reach over OS2 with MPO-12/APC connector and supports 4x100G DR breakout. -
Vendor:NVIDIA
NVIDIA 900-5G195-2501-000 | RTX Pro 4000 SFF 24GB GDDR7 Graphics Card, 70W, PCIe 5.0
900-5G195-2501-000
In stock
Vendor:NVIDIANVIDIA 900-5G195-2501-000 | RTX Pro 4000 SFF 24GB GDDR7 Graphics Card, 70W, PCIe 5.0
The NVIDIA RTX Pro 4000 SFF Blackwell is a professional low-profile workstation graphics card designed for compact AI workstations and small form factor systems. Powered by Blackwell architecture with 24GB GDDR7 ECC memory, 8,960 CUDA cores, and 280 fifth-generation Tensor Cores, it delivers breakthrough AI performance up to 770 AI TOPS while maintaining a 70W thermal envelope. With PCIe slot-only power and a dual-slot low-profile design, it's ideal for space-constrained professional environments running CAD, 3D rendering, AI inference, and scientific visualization workloads. -
Vendor:Cisco
Cisco HCI-GPU-A16-M6 | NVIDIA A16 GPU, 64GB (4x16GB) GDDR6, PCIe 4.0, VDI
HCI-GPU-A16-M6
Stock Status: Enquire
Vendor:CiscoCisco HCI-GPU-A16-M6 | NVIDIA A16 GPU, 64GB (4x16GB) GDDR6, PCIe 4.0, VDI
The Cisco HCI-GPU-A16-M6 delivers enterprise-grade virtual desktop infrastructure with the NVIDIA A16 GPU based on Ampere architecture. Featuring a unique quad-GPU design with 64GB total memory across four independent 16GB GDDR6 GPUs, this dual-slot PCIe 4.0 accelerator supports up to 64 concurrent VDI users per board. Engineered for Cisco UCS and HyperFlex environments, it enables high-density, graphics-rich virtual desktops for knowledge workers and entry-level virtual workstations for CAD and design users. -
Vendor:NVIDIA
NVIDIA 920-9B110-00RH-0D0 | 40x QSFP56 200Gb HDR IB | 2x PSU | C2P airflow | Rail kit | Unmanaged
920-9B110-00RH-0D0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9B110-00RH-0D0 | 40x QSFP56 200Gb HDR IB | 2x PSU | C2P airflow | Rail kit | Unmanaged
Ultra‑low‑latency 1U HDR InfiniBand switch for dense AI/HPC fabrics. The QM8790 unmanaged variant delivers non‑blocking 200Gb/s per port and advanced IB congestion control while relying on an external Subnet Manager (UFM/OpenSM). This configuration uses C2P airflow, includes 2x hot‑swap PSUs, and ships with rails. -
Vendor:Cisco
Cisco HX-GPU-A16 | NVIDIA A16 GPU, 64GB GDDR6, 250W, PCIe Gen4 x16
HX-GPU-A16
Stock Status: Enquire
Vendor:CiscoCisco HX-GPU-A16 | NVIDIA A16 GPU, 64GB GDDR6, 250W, PCIe Gen4 x16
The Cisco HX-GPU-A16 is a high-density VDI graphics accelerator featuring the NVIDIA A16 with four Ampere architecture GPUs on a single PCIe card. Designed for virtual desktop infrastructure deployments, it delivers 64GB total GDDR6 ECC memory and 250W TDP, providing double the user density of previous generations. Ideal for enterprise virtual workstation and virtual PC environments requiring graphics-rich performance and scalability. -
Vendor:NVIDIA
NVIDIA 980-9I99F-00H002 | 200G to 2x100G QSFP56 Breakout Cable, 2m, Passive DAC
980-9I99F-00H002
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I99F-00H002 | 200G to 2x100G QSFP56 Breakout Cable, 2m, Passive DAC
The NVIDIA 980-9I99F-00H002 is a 200Gb/s to 2x100Gb/s passive copper breakout cable designed for high-density data center connectivity. This 2-meter direct attach copper cable splits one QSFP56 port into two QSFP56 ports, supporting both 200G Ethernet and InfiniBand HDR applications. Ideal for short-reach spine-leaf architectures, AI/ML clusters, and high-performance computing environments requiring cost-effective, low-power interconnects. -
Vendor:NVIDIA
NVIDIA 980-9I98G-00H01A | 200G to 2x100G QSFP56 Breakout DAC, 1.5m Passive Copper
980-9I98G-00H01A
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I98G-00H01A | 200G to 2x100G QSFP56 Breakout DAC, 1.5m Passive Copper
The NVIDIA 980-9I98G-00H01A is a passive copper breakout cable designed for high-density data center applications requiring 200Gb/s to dual 100Gb/s connectivity. This 1.5-meter QSFP56 to 2xQSFP56 splitter cable supports InfiniBand HDR and 200GbE networking, delivering low-latency, cost-effective interconnects for server-to-switch and GPU cluster deployments. Ideal for connecting 200G network infrastructure to dual 100G endpoints within racks. -
Vendor:NVIDIA
NVIDIA 900-9X721-003N-DT0 | 1x 400G Eth/IB VPI, PCIe Gen5 x16, RDMA RoCEv2, SR-IOV, GPUDirect, PTP
900-9X721-003N-DT0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-9X721-003N-DT0 | 1x 400G Eth/IB VPI, PCIe Gen5 x16, RDMA RoCEv2, SR-IOV, GPUDirect, PTP
Single‑port 400G VPI adapter for high‑throughput Ethernet or InfiniBand connectivity in AI/HPC clusters and NVMe‑oF storage. PCIe Gen5 x16 host interface with advanced offloads: RDMA (RoCE v2), GPUDirect RDMA, NVMe‑oF, inline IPsec/TLS, and PTP hardware timestamping for microsecond‑level determinism.
