650 Search Results for "nvidia connectx-6"
-
Vendor:Cisco
Cisco NC55-6X2H-DWDM-BM | 6x200G DWDM line card | MACsec (802.1AE) | coherent optics-ready | NCS 5500
NC55-6X2H-DWDM-BM
Stock Status: Enquire
Vendor:CiscoCisco NC55-6X2H-DWDM-BM | 6x200G DWDM line card | MACsec (802.1AE) | coherent optics-ready | NCS 5500
High-density 6-port 200G DWDM line card enabling scalable long-haul or metro core transport on NCS 5500 platforms. Supports MACsec encryption and coherent pluggable optics (sold separately) for flexible wavelength and reach options. Ideal for high-capacity interconnects where security and spectral efficiency matter. -
Vendor:Cisco
Cisco UCSC-P-M6DD100GFO | 2x100GbE QSFP56, PCIe 4.0 x16, No‑crypto (NC) firmware
UCSC-P-M6DD100GFO
Stock Status: Enquire
Vendor:CiscoCisco UCSC-P-M6DD100GFO | 2x100GbE QSFP56, PCIe 4.0 x16, No‑crypto (NC) firmware
Dual-port 100GbE QSFP56 PCIe 4.0 x16 network adapter designed for high-throughput, low-latency data center fabrics. This OEM no‑crypto variant has hardware encryption features disabled while retaining RDMA/RoCEv2, SR‑IOV, and advanced stateless offloads for performance. -
Vendor:Cisco
Cisco UCSC-P-Q6D32GF-D | 2x32GFC Fibre Channel HBA, PCIe Gen3 x8, NVMe/FC, SR-IOV
UCSC-P-Q6D32GF-D
Stock Status: Enquire
Vendor:CiscoCisco UCSC-P-Q6D32GF-D | 2x32GFC Fibre Channel HBA, PCIe Gen3 x8, NVMe/FC, SR-IOV
Dual-port 32G Fibre Channel HBA for enterprise SAN connectivity, providing consistent, lossless performance with support for NVMe/FC and FCP-SCSI. Backward-compatible with 16G/8G, it adds T10 PI for integrity and NPIV/SR-IOV for virtualization scale. A robust choice for latency-sensitive databases, VDI, and backup windows. -
Vendor:Cisco
Cisco HCI-GPU-A100-80M6 | A100 80GB GPU Accelerator, 300W PCIe 4.0, Passive
HCI-GPU-A100-80M6
Stock Status: Enquire
Vendor:CiscoCisco HCI-GPU-A100-80M6 | A100 80GB GPU Accelerator, 300W PCIe 4.0, Passive
The Cisco HCI-GPU-A100-80M6 is an NVIDIA A100 Tensor Core GPU accelerator with 80GB HBM2e memory, designed for demanding AI training, deep learning inference, and high-performance computing workloads in data center environments. Built on NVIDIA's Ampere architecture, it delivers 312 TFLOPS FP16 performance and 2,039 GB/s memory bandwidth, with Multi-Instance GPU capability supporting up to seven isolated GPU instances. The passively cooled, dual-slot PCIe 4.0 x16 form factor integrates into standard Cisco UCS rack servers for scalable compute acceleration. -
Vendor:NVIDIA
NVIDIA 920-9B10A-00FH-0D0 | HDR 200Gb/s InfiniBand chassis module | ports: chassis-integrated | uplinks: backplane HDR 200G | PoE: none | license: UFM-managed
920-9B10A-00FH-0D0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9B10A-00FH-0D0 | HDR 200Gb/s InfiniBand chassis module | ports: chassis-integrated | uplinks: backplane HDR 200G | PoE: none | license: UFM-managed
Director-class InfiniBand HDR (200Gb/s) chassis component for scaling high-performance fabrics. This module augments capacity and resiliency within an HDR chassis, delivering consistent low latency and high bandwidth for AI and HPC environments. It is administered via the chassis supervisor and UFM, enabling fabric-wide telemetry and lifecycle operations. The host chassis supplies power and cooling. -
Vendor:NVIDIA
NVIDIA 920-9B110-00FH-0D4 | HDR 200Gb/s InfiniBand chassis module | ports: chassis-integrated | uplinks: backplane HDR 200G | PoE: none | license: UFM-managed
920-9B110-00FH-0D4
Stock Status: Enquire
Vendor:NVIDIANVIDIA 920-9B110-00FH-0D4 | HDR 200Gb/s InfiniBand chassis module | ports: chassis-integrated | uplinks: backplane HDR 200G | PoE: none | license: UFM-managed
Modular InfiniBand HDR (200Gb/s) component for director-class chassis, delivering high-throughput, low-latency fabric capability for dense HPC and AI clusters. Installed into a compatible HDR chassis, it leverages the backplane for connectivity and is coordinated by the chassis supervisor. UFM provides comprehensive fabric orchestration, telemetry, and health monitoring. -
Vendor:NVIDIA
NVIDIA 980-9I51A-00NS00 | 800G OSFP twin-port | SR8 850nm MMF | 50 m | 2x MPO-12 APC | 2x NDR
980-9I51A-00NS00
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I51A-00NS00 | 800G OSFP twin-port | SR8 850nm MMF | 50 m | 2x MPO-12 APC | 2x NDR
High-density twin-port 800G OSFP optical transceiver using 850nm MMF with two MPO-12 APC interfaces, ideal for building scalable AI/ML and spine–leaf fabrics. Delivers two independent 400G links (aggregate 800G) over short-reach multimode up to 50 m. Flat-top mechanical design for dense thermal envelopes. -
Vendor:Cisco
Cisco UCSAI-P-NC3220 | 2x200GbE QSFP56 DPU, BlueField‑3 B3220, inline IPsec/TLS crypto, PCIe Gen5 x16
UCSAI-P-NC3220
Stock Status: Enquire
Vendor:CiscoCisco UCSAI-P-NC3220 | 2x200GbE QSFP56 DPU, BlueField‑3 B3220, inline IPsec/TLS crypto, PCIe Gen5 x16
Data processing unit that offloads networking, storage, and security from host CPUs. Dual 200GbE QSFP56 ports deliver ultra‑high throughput, while onboard accelerators handle virtualization, encryption, and RDMA to boost application performance in M8 servers. -
Vendor:NVIDIA
NVIDIA 980-9I929-00N002 | 800G AOC breakout | OSFP to 2x QSFP112 | 2 m | 8x100G PAM4 to 2x4x100G | MMF 850nm
980-9I929-00N002
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I929-00N002 | 800G AOC breakout | OSFP to 2x QSFP112 | 2 m | 8x100G PAM4 to 2x4x100G | MMF 850nm
High-performance 800G breakout AOC that maps one OSFP 8x100G PAM4 port to two QSFP112 4x100G PAM4 ports. Ideal for fan-out from 800G switch ports to dual 400G endpoints over short-reach MMF. Lightweight, low-power alternative to discrete transceivers. -
Vendor:NVIDIA
NVIDIA 900-5G192-2571-000 | RTX 4000 SFF Ada 20GB Graphics Card, 70W, 4x miniDP
900-5G192-2571-000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-5G192-2571-000 | RTX 4000 SFF Ada 20GB Graphics Card, 70W, 4x miniDP
The NVIDIA RTX 4000 SFF Ada Generation delivers full-size workstation performance in a compact, dual-slot, low-profile form factor. Built on the Ada Lovelace architecture with 6,144 CUDA cores, 48 third-generation RT Cores, and 192 fourth-generation Tensor Cores, it features 20GB of ECC GDDR6 memory for professional rendering, AI acceleration, and compute workloads. Ideal for CAD, 3D modeling, video editing, and VDI in space-constrained workstations. -
Vendor:Cisco
Cisco HX-GPU-P40 | Tesla P40 GPU Accelerator, 24GB GDDR5, 3840 CUDA Cores
HX-GPU-P40
Stock Status: Enquire
Vendor:CiscoCisco HX-GPU-P40 | Tesla P40 GPU Accelerator, 24GB GDDR5, 3840 CUDA Cores
The Cisco HX-GPU-P40 is an NVIDIA Tesla P40 GPU accelerator designed for Cisco HyperFlex HX-Series servers, delivering exceptional deep learning inference and virtual workstation performance. Built on the Pascal architecture with 3840 CUDA cores and 24GB GDDR5 memory, it provides 12 TFLOPS of single-precision compute performance and 47 TOPS of INT8 inference throughput. This passively cooled, dual-slot PCIe 3.0 x16 card is optimized for AI deployment, graphics virtualization, and GPU-accelerated workloads in data center environments. -
Vendor:Cisco
Cisco N7K-F306CK-25 | 6x 100GbE CPAK line card | 1-slot | Fabric-2 compatible
N7K-F306CK-25
Stock Status: Enquire
Vendor:CiscoCisco N7K-F306CK-25 | 6x 100GbE CPAK line card | 1-slot | Fabric-2 compatible
High-capacity 100GbE line card providing 6 CPAK interfaces for Nexus 7000 Series core/aggregation deployments. Delivers line-rate Layer 2/Layer 3 100GbE with NX-OS services, occupying a single slot and integrating with Fabric-2 backplane for high throughput. Supports a range of CPAK optics for long-reach and short-reach applications. -
Vendor:Cisco
Cisco UCSC-885L-M8-M351 | GPU server | 8x MI355X accelerators | 2x ConnectX-7 | 3TB memory | 8x E1.S NVMe
UCSC-885L-M8-M351
Stock Status: Enquire
Vendor:CiscoCisco UCSC-885L-M8-M351 | GPU server | 8x MI355X accelerators | 2x ConnectX-7 | 3TB memory | 8x E1.S NVMe
High-density AI/compute platform preconfigured with 8x MI355X accelerator modules, dual ConnectX-7 adapters for high-throughput fabrics, 3TB system memory, and 8x E1.S NVMe bays for fast local storage. Ideal for training, inference, and HPC workloads where dense GPU, fast networking, and serviceable E1.S media are priorities. -
Vendor:Cisco
Cisco E-SSD-U2N-4TB | U.2 NVMe SSD 4TB 2.5in | PCIe NVMe | for UCS-E M6
E-SSD-U2N-4TB
Stock Status: Enquire
Vendor:CiscoCisco E-SSD-U2N-4TB | U.2 NVMe SSD 4TB 2.5in | PCIe NVMe | for UCS-E M6
High-capacity U.2 NVMe 2.5-inch SSD designed for UCS-E M6 compute modules, combining NVMe performance with 4 TB capacity for data-intensive applications, analytics, and consolidation of workloads. -
Vendor:NVIDIA
NVIDIA 900-82888-0040-000 | Jetson AGX Xavier AI Compute Module, 32GB, 512-Core Volta GPU, 64 Tensor Cores
900-82888-0040-000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-82888-0040-000 | Jetson AGX Xavier AI Compute Module, 32GB, 512-Core Volta GPU, 64 Tensor Cores
The NVIDIA Jetson AGX Xavier 32GB module delivers up to 32 TOPS of AI computing performance in a compact 100 x 87mm form factor consuming under 30 watts. Powered by an 8-core Carmel ARMv8.2 CPU and 512-core Volta GPU with 64 Tensor Cores, this system-on-module is designed for autonomous machines, robotics, industrial AI, and edge computing applications. It provides 20X the performance and 10X the energy efficiency compared to its predecessor, making it ideal for real-time AI inferencing in manufacturing, logistics, agriculture, smart cities, and healthcare. -
Vendor:NVIDIA
NVIDIA 980-9I58J-00N150 | IB/Ethernet MPO-12 SMF (OS2) trunk | 1310 nm | PSM4 40/100G-ready | 150 m | MPO–MPO | Yellow
980-9I58J-00N150
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I58J-00N150 | IB/Ethernet MPO-12 SMF (OS2) trunk | 1310 nm | PSM4 40/100G-ready | 150 m | MPO–MPO | Yellow
High-quality MPO-12 single-mode trunk for InfiniBand and Ethernet fabrics. Using OS2 (9/125 µm) fiber optimized for 1310 nm PSM4 optics, the 150 m assembly offers low-loss connectivity between MPO-12 ports across extended data hall runs. -
Vendor:NVIDIA
NVIDIA MSN3420-CB2RC | 48x 10/25G SFP28 access | 12x 100G QSFP28 uplinks | Cumulus Linux | dual PSU | C2P airflow | 1U
MSN3420-CB2RC
Stock Status: Enquire
Vendor:NVIDIANVIDIA MSN3420-CB2RC | 48x 10/25G SFP28 access | 12x 100G QSFP28 uplinks | Cumulus Linux | dual PSU | C2P airflow | 1U
High-performance 1U leaf switch delivering 48x SFP28 access (10/25G) and 12x 100G QSFP28 uplinks for scalable spine connectivity. Cumulus Linux enables open, automated networking with EVPN-VXLAN, BGP, and robust L2/L3. Built-in high availability with hot-swappable dual PSUs and fans, using cable-to-port (C2P) airflow. -
Vendor:NVIDIA
NVIDIA MFS1S00-H003V | 200G QSFP56 AOC | IB HDR | 850nm | 3m | QSFP56-to-QSFP56
MFS1S00-H003V
Stock Status: Enquire
Vendor:NVIDIANVIDIA MFS1S00-H003V | 200G QSFP56 AOC | IB HDR | 850nm | 3m | QSFP56-to-QSFP56
High-performance active optical cable for 200Gb/s InfiniBand HDR links. QSFP56-to-QSFP56 design delivers low latency, low weight, and superior reach versus DAC, ideal for spine–leaf and GPU/HPC interconnects. LSZH jacket and black pull tab for clean, safe data center deployments. -
Vendor:NVIDIA
NVIDIA 900-9D3B4-00CV-EA0 | Dual-port 200GbE/NDR200 IB SuperNIC, FHHL, PCIe Gen5, E‑Series
900-9D3B4-00CV-EA0
Stock Status: Enquire
Vendor:NVIDIANVIDIA 900-9D3B4-00CV-EA0 | Dual-port 200GbE/NDR200 IB SuperNIC, FHHL, PCIe Gen5, E‑Series
E‑Series FHHL SuperNIC with dual 200GbE Ethernet (default) or NDR200 InfiniBand, engineered for ultra‑low‑latency cloud, AI, and storage fabrics with advanced networking offloads. -
Vendor:NVIDIA
NVIDIA MCP7H50-H002R26 | Passive copper breakout DAC | IB HDR 200G to 2x100G | QSFP56 to 2x QSFP56 | 2m
MCP7H50-H002R26
Stock Status: Enquire
Vendor:NVIDIANVIDIA MCP7H50-H002R26 | Passive copper breakout DAC | IB HDR 200G to 2x100G | QSFP56 to 2x QSFP56 | 2m
HDR breakout DAC that splits one 200G QSFP56 port into two 100G QSFP56 links over a 2m passive copper assembly. Designed for short-to-medium reach fan-out connections with minimal latency and no power draw. -
Vendor:NVIDIA
NVIDIA 980-9IAM5-00X001 | MCA4K50 | 1600G OSFP Active Copper Cable | Reach 1.1m | 1.6T Ethernet | Connector: OSFP‑to‑OSFP
980-9IAM5-00X001
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9IAM5-00X001 | MCA4K50 | 1600G OSFP Active Copper Cable | Reach 1.1m | 1.6T Ethernet | Connector: OSFP‑to‑OSFP
Short‑reach 1.6T OSFP active copper cable with integrated heat sinks on both ends for superior thermal control in tightly packed racks. The 1.1m length is ideal for within‑rack connections that demand the lowest latency and minimal power. -
Vendor:NVIDIA
NVIDIA 980-9I30I-00NM00 | 800G OSFP twin-port | 2xNDR (IB) | 1310nm SMF | 2xMPO-12 APC | up to 100m
980-9I30I-00NM00
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I30I-00NM00 | 800G OSFP twin-port | 2xNDR (IB) | 1310nm SMF | 2xMPO-12 APC | up to 100m
High‑density twin‑port 800G OSFP transceiver designed for InfiniBand NDR fabrics. Provides two independent 400G NDR links over 1310nm single‑mode fiber via MPO‑12 APC connectors, supporting short‑reach deployments up to 100 m in AI/ML clusters and HPC environments. -
Vendor:NVIDIA
NVIDIA 980-9I08O-00W010 | QSFP-DD 400G AOC | 8x50G PAM4 | 850nm MMF | 10m reach | QSFP-DD to QSFP-DD
980-9I08O-00W010
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I08O-00W010 | QSFP-DD 400G AOC | 8x50G PAM4 | 850nm MMF | 10m reach | QSFP-DD to QSFP-DD
10‑meter 400G QSFP‑DD active optical cable designed for flexible rack‑to‑rack or row deployments. Delivers consistent latency and signal integrity using 8x50G PAM4 lanes over integrated multimode fiber at 850nm, minimizing EMI and simplifying installation in high‑density environments. -
Vendor:Cisco
Cisco UCSC-885A-M8-H20 | AI server | H200 GPUs | 2x ConnectX-7 400G | 15TB RAM
UCSC-885A-M8-H20
Stock Status: Enquire
Vendor:CiscoCisco UCSC-885A-M8-H20 | AI server | H200 GPUs | 2x ConnectX-7 400G | 15TB RAM
Next-generation AI server featuring NVIDIA H200 accelerators paired with dual ConnectX-7 400G-class adapters for extreme bandwidth and low latency across AI fabrics. With 15TB of installed memory, it’s tuned for large-scale training, fine-tuning, and high-performance inference, and integrates seamlessly with UCS management.
