649 Search Results for "nvidia connectx-6"
-
Vendor:NVIDIA
NVIDIA 900-9X6AF-0016-ST2 | 1x QSFP28 100G InfiniBand EDR | PCIe 4.0 x8 | Low-profile | RDMA, GPUDirect, Adaptive Routing
900-9X6AF-0016-ST2
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-9X6AF-0016-ST2 | 1x QSFP28 100G InfiniBand EDR | PCIe 4.0 x8 | Low-profile | RDMA, GPUDirect, Adaptive Routing
High-throughput InfiniBand adapter for HPC and AI clusters, providing 100G EDR connectivity with ultra-low latency and advanced congestion control. QSFP28 interface supports short- and long-reach cabling options. PCIe 4.0 x8 host bandwidth and GPUDirect RDMA enable efficient, direct data paths for accelerated compute workflows. Built for dense deployments with a low-profile form factor. -
Vendor:NVIDIA
NVIDIA MUA9602H-2SRS | UFM 3.0 appliance | 1U | 2x ConnectX-7 NDR single-port 400Gb/s InfiniBand adapters (2x NDR 400G ports total) | Telemetry/Enterprise ready
MUA9602H-2SRS
Stock Status: Enquire
Vendor:NVIDIANVIDIA MUA9602H-2SRS | UFM 3.0 appliance | 1U | 2x ConnectX-7 NDR single-port 400Gb/s InfiniBand adapters (2x NDR 400G ports total) | Telemetry/Enterprise ready
High-performance UFM 3.0 appliance engineered for InfiniBand NDR fabrics. The 1U platform integrates two ConnectX-7 single-port 400Gb/s adapters, providing two NDR 400G ports to power advanced telemetry and enterprise fabric control. Ideal for next-generation AI and HPC clusters requiring real-time visibility and automation. -
Vendor:NVIDIA
NVIDIA 900-9X720-007N-SN1 | 4x 400G Eth/IB VPI, PCIe Gen5 x32, RDMA RoCEv2, SR-IOV, GPUDirect, PTP
900-9X720-007N-SN1
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-9X720-007N-SN1 | 4x 400G Eth/IB VPI, PCIe Gen5 x32, RDMA RoCEv2, SR-IOV, GPUDirect, PTP
Quad-port VPI adapter delivering up to 4x 400GbE or 400Gb/s InfiniBand for AI/HPC fabrics, accelerated storage, and ultra‑low‑latency cloud. PCIe Gen5 x32 provides massive host bandwidth with advanced offloads: RDMA (RoCE v2), GPUDirect RDMA, NVMe‑oF, inline IPsec/TLS, and IEEE 1588 PTP hardware timestamping for precision timing. -
Vendor:NVIDIA
NVIDIA 920-9N302-00R7-0C0 | Spectrum-3 64-Port 100GbE Switch, 6.4Tbps, Layer 3
920-9N302-00R7-0C0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9N302-00R7-0C0 | Spectrum-3 64-Port 100GbE Switch, 6.4Tbps, Layer 3
The NVIDIA MSN4600-CS2RC is a Spectrum-3 based 2U open Ethernet switch designed for spine and super-spine deployments in large-scale data centers and cloud environments. With 64 QSFP28 ports delivering 100GbE connectivity, 6.4 Tb/s non-blocking switching capacity, and 8.4 billion packets per second processing, it supports diverse Ethernet speeds from 10G to 100G with flexible breakout options. Pre-loaded with Cumulus Linux, this switch features dual redundant AC power supplies, x86 CPU for advanced management, and C2P airflow for optimized cooling. -
Vendor:NVIDIA
NVIDIA 980-9I693-00NS00 | 400Gb InfiniBand NDR QSFP112, 850nm MMF, 50m reach, MPO‑12 APC
980-9I693-00NS00
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I693-00NS00 | 400Gb InfiniBand NDR QSFP112, 850nm MMF, 50m reach, MPO‑12 APC
High-bandwidth 400Gb InfiniBand NDR optical transceiver for QSFP112 ports. Engineered for low-latency HPC fabrics and AI clusters over multimode fiber with up to 50 m reach on OM4 infrastructure using MPO‑12 APC connectivity. -
Vendor:NVIDIA
NVIDIA 900-9X7AH-0079-DTZ | 200GbE 1x QSFP56, PCIe 5.0 x16, HHHL
900-9X7AH-0079-DTZ
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-9X7AH-0079-DTZ | 200GbE 1x QSFP56, PCIe 5.0 x16, HHHL
Data‑center‑class 200GbE PCIe 5.0 adapter built for intensive east‑west traffic, storage acceleration, and GPU‑centric workloads. Delivers RDMA, inline crypto, and overlay offloads to maximize application performance and efficiency. -
Vendor:NVIDIA
NVIDIA 900-9D3B6-00SC-EA0 | BlueField-3 B3210E DPU | 2x100GbE/HDR100, 2xQSFP56, PCIe x16, FHHL
900-9D3B6-00SC-EA0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-9D3B6-00SC-EA0 | BlueField-3 B3210E DPU | 2x100GbE/HDR100, 2xQSFP56, PCIe x16, FHHL
Programmable DPU for accelerating networking, storage, and security. Dual-mode ports support 100GbE or HDR100 InfiniBand with QSFP56 optics. Onboard acceleration offloads virtualization, NVMe-oF/TCP, RoCE v2, OVS, and inline crypto to free host CPU and improve latency and throughput. Ideal for secure multi-tenant clouds and data center consolidation. -
Vendor:NVIDIA
NVIDIA 980-9I46L-00H002 | 400G Breakout Cable, OSFP to 2x QSFP56, 2m, HDR
980-9I46L-00H002
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I46L-00H002 | 400G Breakout Cable, OSFP to 2x QSFP56, 2m, HDR
The NVIDIA 980-9I46L-00H002 is a passive copper breakout cable designed for high-performance InfiniBand HDR and 400GbE data center connectivity. It splits one 400Gb/s OSFP port into two 200Gb/s QSFP56 ports, enabling efficient connections between NDR or 400GbE switches and legacy HDR infrastructure. Ideal for short-reach applications within racks, this 2-meter cable delivers cost-effective, low-latency performance without requiring external power. -
Vendor:Cisco
Cisco HX-GPU-RTX6000 | RTX 6000 Graphics Card, 24GB GDDR6, 4608 CUDA Cores
HX-GPU-RTX6000
Stock Status: Enquire
Vendor:CiscoCisco HX-GPU-RTX6000 | RTX 6000 Graphics Card, 24GB GDDR6, 4608 CUDA Cores
The Cisco HX-GPU-RTX6000 is an NVIDIA Quadro RTX 6000 passive graphics card designed for UCS and HyperFlex servers. Built on the Turing architecture with 4608 CUDA cores, 576 Tensor cores, and 72 RT cores, it accelerates AI, deep learning, rendering, and virtualized workstation workloads in data center environments. The 24GB GDDR6 memory and passive thermal design enable high-density GPU deployments for demanding visual computing and scientific applications. -
Vendor:NVIDIA
NVIDIA 900-53669-2500-000 | NVLink Bridge 3-Slot, 112GB/s, Ampere Generation
900-53669-2500-000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-53669-2500-000 | NVLink Bridge 3-Slot, 112GB/s, Ampere Generation
The NVIDIA NVLink Bridge 3-slot enables high-speed GPU-to-GPU interconnect for dual Ampere-based RTX A-series professional graphics cards. Designed for systems with three PCI-Express slot spacing, this bridge provides up to 112 GB/s bidirectional bandwidth, enabling memory pooling and performance scaling for demanding visual computing, AI, data science, rendering, and simulation workloads. -
Vendor:NVIDIA
NVIDIA 900-54935-2500-000 | NVLink bridge, 3-slot spacing, RTX 5000 compatible, NVLink 2.0, up to 50 Gb/s aggregate
900-54935-2500-000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-54935-2500-000 | NVLink bridge, 3-slot spacing, RTX 5000 compatible, NVLink 2.0, up to 50 Gb/s aggregate
High-bandwidth NVLink 2.0 bridge engineered to connect two RTX 5000 workstation GPUs with 3-slot spacing, enabling larger combined frame buffers and higher inter-GPU bandwidth for demanding visualization and compute workloads. Confirm your motherboard provides 3-slot center-to-center spacing between the two PCIe x16 slots housing the GPUs. -
Vendor:NVIDIA
NVIDIA 920-9N302-00F7-0C2 | Spectrum-3 64-Port 100GbE Switch, 6.4Tb/s, 2U
920-9N302-00F7-0C2
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9N302-00F7-0C2 | Spectrum-3 64-Port 100GbE Switch, 6.4Tb/s, 2U
The NVIDIA MSN4600-CS2FC is a high-performance Spectrum-3 based 100GbE data center switch designed for spine and super-spine architectures in large virtualized environments. With 64 QSFP28 ports supporting flexible speeds from 10GbE to 100GbE, this 2U switch delivers 6.4Tb/s throughput and 8.4Bpps processing capacity with ultra-low 650ns latency. Pre-loaded with Cumulus Linux open network operating system and featuring dual hot-swappable AC power supplies with P2C airflow, it provides enterprise-grade reliability for hyperscale data centers, cloud environments, AI/ML workloads, and software-defined networking deployments. -
Vendor:NVIDIA
NVIDIA 920-9N42C-00RB-7C0 | Spectrum-4 64-Port 400G Switch, 25.6Tbps, 2x 25G SFP28
920-9N42C-00RB-7C0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9N42C-00RB-7C0 | Spectrum-4 64-Port 400G Switch, 25.6Tbps, 2x 25G SFP28
The NVIDIA SN5400 is a Spectrum-4 based 400GbE data center switch delivering 25.6Tbps switching capacity in a 2U form factor. Equipped with 64 QSFP56-DD ports supporting speeds from 1GbE to 400GbE, plus 2 additional 25GbE SFP28 ports, this switch is purpose-built for AI infrastructure, hyperscale cloud fabrics, and high-performance spine/leaf architectures. Pre-loaded with Cumulus Linux and featuring dual hot-swappable AC power supplies, connector-to-power airflow, and an x86 CPU with secure boot, the SN5400 delivers wire-speed performance with 33.3 billion packets per second forwarding rate and 160MB packet buffer for demanding AI, storage, and cloud workloads. -
Vendor:NVIDIA
NVIDIA 930-9XBRK-00MB-000 | Full-height PCIe bracket | Dual QSFP56 port cutouts | For 2-port adapters
930-9XBRK-00MB-000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 930-9XBRK-00MB-000 | Full-height PCIe bracket | Dual QSFP56 port cutouts | For 2-port adapters
Replacement full-height (tall) PCIe bracket designed for dual-port QSFP56 network adapters. Provides correct port alignment and secure chassis mounting in standard-height server slots; suitable for specified 2x QSFP56 adapter models. -
Vendor:HPE
HPE P10180-B21 | 200GbE 1xQSFP56, PCIe Gen4 x16, ConnectX-6 EN, RDMA/RoCEv2, SR-IOV, NVMe-oF
P10180-B21
Stock Status: Enquire
Vendor:HPEHPE P10180-B21 | 200GbE 1xQSFP56, PCIe Gen4 x16, ConnectX-6 EN, RDMA/RoCEv2, SR-IOV, NVMe-oF
High-throughput 200GbE single-port QSFP56 PCIe Gen4 adapter built on ConnectX-6 for ultra‑low latency, virtualization offloads, and NVMe‑oF acceleration in modern data centers. Ideal for HPC, storage, and cloud workloads requiring RoCEv2 and advanced encapsulation offloads. -
Vendor:NVIDIA
NVIDIA 900-5G195-2551-000 | RTX PRO 2000 Graphics Card, 16GB GDDR7 ECC, PCIe 5.0 x8
900-5G195-2551-000
In stock
Vendor:NVIDIANVIDIA 900-5G195-2551-000 | RTX PRO 2000 Graphics Card, 16GB GDDR7 ECC, PCIe 5.0 x8
The NVIDIA RTX PRO 2000 Blackwell is a compact professional graphics card built on the advanced Blackwell architecture, delivering exceptional AI and visualization performance in a power-efficient 70W design. Featuring 16GB of ECC GDDR7 memory, 4,352 CUDA cores, 5th Gen Tensor Cores, and 4th Gen Ray Tracing Cores, it accelerates CAD, 3D modeling, AI workflows, and neural rendering for professional workstations. The dual-slot, low-profile form factor with four mini DisplayPort 2.1b outputs makes it ideal for compact workstations requiring multi-display support and enterprise-grade reliability. -
Vendor:NVIDIA
NVIDIA 900-53651-0000-000 | 2-Way NVLink Bridge | 2-Slot Spacing | High-bandwidth GPU-to-GPU Interconnect
900-53651-0000-000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-53651-0000-000 | 2-Way NVLink Bridge | 2-Slot Spacing | High-bandwidth GPU-to-GPU Interconnect
2-way NVLink bridge for connecting two compatible professional GPUs installed with 2-slot spacing, enabling high-bandwidth peer-to-peer links for accelerated compute, rendering, and AI workloads. -
Vendor:NVIDIA
NVIDIA 980-9I445-00H003 | 200G QSFP56 to 2×100G QSFP56 AOC splitter, IB HDR/200GbE, 850nm MMF, 3m
980-9I445-00H003
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I445-00H003 | 200G QSFP56 to 2×100G QSFP56 AOC splitter, IB HDR/200GbE, 850nm MMF, 3m
Fan‑out active optical cable for breaking a 200G port into two independent 100G links. Designed for spine–leaf or switch–adapter aggregation where short 3 m reach is ideal. Integrated QSFP56 optical engines provide low‑latency, high‑reliability InfiniBand HDR100 and 2×100GbE connections without separate transceivers or patch cords. -
Vendor:NVIDIA
NVIDIA 900-2G193-0000-000 | L4 Ada Lovelace GPU, 24GB GDDR6, 72W TDP, Single-Slot
900-2G193-0000-000
In stock
Vendor:NVIDIANVIDIA 900-2G193-0000-000 | L4 Ada Lovelace GPU, 24GB GDDR6, 72W TDP, Single-Slot
The NVIDIA L4 is a low-profile, energy-efficient Tensor Core GPU powered by the Ada Lovelace architecture, designed for AI inference, video processing, graphics virtualization, and data center workloads. With 24GB of GDDR6 memory, 7680 CUDA cores, and a 72W TDP, the L4 delivers universal acceleration in a compact single-slot form factor. Ideal for edge servers, cloud environments, and data centers requiring high throughput and low latency with minimal power consumption. -
Vendor:NVIDIA
NVIDIA MCX623105AC-VDAT | 200GbE QSFP56, PCIe 4.0, active cooling, single-port adapter
MCX623105AC-VDAT
Stock Status: Enquire
Vendor:NVIDIANVIDIA MCX623105AC-VDAT | 200GbE QSFP56, PCIe 4.0, active cooling, single-port adapter
Single‑port 200GbE adapter engineered for AI/HPC, storage, and cloud workloads requiring extreme throughput and low latency. QSFP56 port supports 200G optics and cables with RoCE v2 RDMA and advanced offloads to reduce CPU utilization. Active cooling for sustained performance. -
Vendor:NVIDIA
NVIDIA 920-9B210-00RN-0M2 | Quantum-2 64-Port NDR InfiniBand Switch, 51.2Tbps
920-9B210-00RN-0M2
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9B210-00RN-0M2 | Quantum-2 64-Port NDR InfiniBand Switch, 51.2Tbps
The NVIDIA MQM9700-NS2R is a Quantum-2 based NDR InfiniBand switch delivering 64 ports of 400Gb/s connectivity via 32 OSFP connectors in a compact 1U chassis. With 51.2Tbps aggregated bidirectional throughput and over 66.5 billion packets per second capacity, this managed switch is engineered for AI workloads, high-performance computing, and extreme-scale data center environments requiring ultra-low latency and maximum bandwidth. The C2P airflow design ensures optimal cooling in reverse airflow rack configurations. -
Vendor:NVIDIA
NVIDIA 920-9B210-00RN-0D0 | Quantum-2 64-Port NDR InfiniBand Switch, 32x OSFP
920-9B210-00RN-0D0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9B210-00RN-0D0 | Quantum-2 64-Port NDR InfiniBand Switch, 32x OSFP
The NVIDIA MQM9790-NS2R Quantum-2 NDR InfiniBand switch delivers 64 ports of 400Gb/s throughput in a compact 1U design, ideal for AI, HPC, and high-performance computing workloads. With 32 OSFP connectors supporting 51.2Tb/s aggregate bidirectional bandwidth and 66.5 billion packets per second capacity, this unmanaged switch provides ultra-low latency connectivity for data center fabric deployments. The C2P airflow configuration ensures efficient cooling in rear-to-front airflow rack environments. -
Vendor:NVIDIA
NVIDIA 900-2G179-0020-101 | A2 Tensor Core 16GB GPU, PCIe 4.0 x8, 40-60W TDP
900-2G179-0020-101
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-2G179-0020-101 | A2 Tensor Core 16GB GPU, PCIe 4.0 x8, 40-60W TDP
The NVIDIA A2 Tensor Core GPU delivers entry-level AI inference acceleration with exceptional power efficiency for edge deployments and compact server environments. Built on the Ampere architecture with 16GB GDDR6 memory and 1280 CUDA cores, it provides 4.5 TFLOPS FP32 performance and up to 72 TOPS INT4 tensor performance in a single-slot, low-profile form factor. Ideal for intelligent video analytics, machine learning inference, and virtual desktop infrastructure workloads where space and power constraints are critical. -
Vendor:NVIDIA
NVIDIA 920-9B210-00FN-0D0 | Quantum-2 QM9790 64-Port 400G NDR InfiniBand Switch, 1U
920-9B210-00FN-0D0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9B210-00FN-0D0 | Quantum-2 QM9790 64-Port 400G NDR InfiniBand Switch, 1U
The NVIDIA QM9790 (920-9B210-00FN-0D0) is an unmanaged 1U NDR InfiniBand switch delivering 64 ports of 400Gb/s connectivity via 32 OSFP cages with 51.2Tb/s aggregate bidirectional throughput and 66.5 billion packets per second capacity. Built on the Quantum-2 ASIC, this switch is engineered for extreme-scale AI training clusters, HPC environments, and data-intensive workloads requiring ultra-low latency interconnects. The P2C airflow design ensures optimal thermal performance in high-density rack deployments.
