581 Search Results for "NVIDIA ConnectX-6"
-
Vendor:Juniper
Juniper CTP150-CBL-DB15-DCE-F | HD-26 to DB15 interface cable | DCE, female DB15 | for CTP150
CTP150-CBL-DB15-DCE-F
Stock Status: Enquire
Vendor:JuniperJuniper CTP150-CBL-DB15-DCE-F | HD-26 to DB15 interface cable | DCE, female DB15 | for CTP150
Interface cable for CTP150 ports that adapts HD-26 to DB15 with DCE orientation and a female DB15 connector, enabling straightforward connections to compatible serial/voice equipment. -
Vendor:Cisco
Cisco HX-GPU-P100-16G | Tesla P100 GPU Accelerator, 16GB HBM2, 3584 CUDA Cores
HX-GPU-P100-16G
Stock Status: Enquire
Vendor:CiscoCisco HX-GPU-P100-16G | Tesla P100 GPU Accelerator, 16GB HBM2, 3584 CUDA Cores
The Cisco HX-GPU-P100-16G is an NVIDIA Tesla P100 GPU accelerator designed for HPC, AI training, and deep learning workloads in Cisco HyperFlex systems. Built on Pascal architecture with 16GB of high-bandwidth HBM2 memory and 3584 CUDA cores, it delivers 9.3 TFLOPS single-precision and 4.7 TFLOPS double-precision performance. The passive cooling design requires adequate server airflow for efficient operation in data center environments. -
Vendor:Cisco
Cisco HX-GPU-A100 | A100 40GB Graphics Card, Ampere Tensor GPU, 250W Passive
HX-GPU-A100
Stock Status: Enquire
Vendor:CiscoCisco HX-GPU-A100 | A100 40GB Graphics Card, Ampere Tensor GPU, 250W Passive
The Cisco HX-GPU-A100 is an NVIDIA A100 Tensor Core GPU designed for high-performance computing, AI training, and data analytics in enterprise data centers. Built on the Ampere architecture with 40GB HBM2 memory and Multi-Instance GPU capability, it delivers breakthrough acceleration for large-scale machine learning, deep learning inference, and scientific computing workloads. The PCIe Gen4 x16 form factor with passive cooling enables flexible integration into Cisco HyperFlex and UCS servers for compute-intensive AI and HPC applications. -
Vendor:NVIDIA
NVIDIA 980-9IAM3-00X002 | MCA4K50 | 1600G OSFP Active Copper Cable | Reach 2m | 1.6T Ethernet | Connector: OSFP‑to‑OSFP
980-9IAM3-00X002
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9IAM3-00X002 | MCA4K50 | 1600G OSFP Active Copper Cable | Reach 2m | 1.6T Ethernet | Connector: OSFP‑to‑OSFP
High‑density 1.6T OSFP active copper cable designed for ultra‑low‑latency, short‑reach switch interconnects. Integrated heat sinks on both OSFP ends improve thermal performance in dense chassis. Ideal for AI/HPC fabrics and spine‑leaf deployments requiring 1600G aggregate bandwidth without the power draw of optical links. -
Vendor:HPE
HPE R9H23C | A2 16GB Tensor Core GPU, PCIe Gen4 x8, 60W, Passive
R9H23C
Stock Status: Enquire
Vendor:HPEHPE R9H23C | A2 16GB Tensor Core GPU, PCIe Gen4 x8, 60W, Passive
The HPE NVIDIA A2 16GB PCIe Accelerator delivers entry-level AI inference and edge computing performance in a compact, power-efficient design. Powered by NVIDIA Ampere architecture with 1280 CUDA cores, 40 Tensor cores, and 16GB GDDR6 memory, this low-profile, single-slot GPU accelerates machine learning inference, computer vision, and analytics workloads in space-constrained server environments. With 40-60W configurable TDP and passive cooling, the A2 enables AI deployment at scale across edge, data center, and cloud infrastructure. -
Vendor:NVIDIA
NVIDIA MCP7Y70-H01A | Speed: 400G→4x100G | Form: OSFP to 4xQSFP56 | Standard: InfiniBand HDR | Wavelength: n/a (passive copper) | Reach: 1.5m | Connector: OSFP<>QSFP56
MCP7Y70-H01A
Stock Status: Enquire
Vendor:NVIDIANVIDIA MCP7Y70-H01A | Speed: 400G→4x100G | Form: OSFP to 4xQSFP56 | Standard: InfiniBand HDR | Wavelength: n/a (passive copper) | Reach: 1.5m | Connector: OSFP<>QSFP56
Passive copper DAC breakout for converting a 400G HDR OSFP host into four 100G QSFP56 endpoints over 1.5m. Ideal for high-throughput, short-reach links in HPC/AI racks with minimal latency and no power draw. -
Vendor:NVIDIA
NVIDIA 980-9I56O-00N015 | MPO-12 trunk | 100/200/400G PSM4/DR4 compatible | 1310 nm SMF | 15 m | 2x MPO-12
980-9I56O-00N015
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I56O-00N015 | MPO-12 trunk | 100/200/400G PSM4/DR4 compatible | 1310 nm SMF | 15 m | 2x MPO-12
MPO‑12 OS2 single‑mode trunk cable for parallel‑optics fabrics at 1310 nm. The 15 m yellow jacket assembly supports DR4/PSM4‑class transceivers for high‑speed Ethernet and InfiniBand, delivering low skew and consistent performance for structured cabling or direct device links. -
Vendor:NVIDIA
NVIDIA 980-9I78I-00A000 | QSFP28‑to‑SFP28 adapter (QSA28) | enables 25G SFP28 in QSFP28 ports | metal housing
980-9I78I-00A000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I78I-00A000 | QSFP28‑to‑SFP28 adapter (QSA28) | enables 25G SFP28 in QSFP28 ports | metal housing
Compact QSFP28‑to‑SFP28 adapter that lets you use an SFP28 optical module or DAC/AOC in a QSFP28 switch or NIC port. Ideal for incremental 25G rollouts, lab environments, or mixed‑speed migration without replacing existing hardware. Plug‑and‑play design preserves port density and simplifies spares management. -
Vendor:Cisco
Cisco HCIX-CPU-I6430 | Xeon Gold 6430 | 32C/64T 2.1GHz, 60MB, 270W | DDR5-4400, 8-ch | LGA4677, PCIe 5.0
HCIX-CPU-I6430
Stock Status: Enquire
Vendor:CiscoCisco HCIX-CPU-I6430 | Xeon Gold 6430 | 32C/64T 2.1GHz, 60MB, 270W | DDR5-4400, 8-ch | LGA4677, PCIe 5.0
A balanced 32-core processor for dense virtualization and general-purpose compute, the Xeon Gold 6430 couples a 2.1GHz base clock with a 60MB cache for consistent multi-VM throughput. Its 8-channel DDR5-4400 memory controller and LGA4677 platform enable high memory bandwidth and next-gen I/O via PCIe 5.0. With a 270W TDP, plan for robust cooling and power delivery in your rack server design. -
Vendor:Cisco
Cisco UCSC-GPU-V100 | Tesla V100 GPU, 16GB HBM2, 5120 CUDA Cores, 640 Tensor
UCSC-GPU-V100
Stock Status: Enquire
Vendor:CiscoCisco UCSC-GPU-V100 | Tesla V100 GPU, 16GB HBM2, 5120 CUDA Cores, 640 Tensor
The Cisco UCSC-GPU-V100 is a data center GPU accelerator powered by NVIDIA Volta architecture, delivering exceptional performance for AI training, deep learning, and high-performance computing workloads. Featuring 16GB HBM2 memory with 900 GB/s bandwidth, 5120 CUDA cores, and 640 Tensor cores, this PCIe 3.0 x16 GPU provides up to 112 TFLOPS of deep learning performance. The passive-cooled, dual-slot design integrates seamlessly into Cisco UCS C240 M5 and C480 M5 rack servers for enterprise AI and scientific computing applications. -
Vendor:Cisco
Cisco UCSC-GPU-V100-32 | Tesla V100 32GB HBM2 GPU, 5120 CUDA, 640 Tensor Cores
UCSC-GPU-V100-32
Stock Status: Enquire
Vendor:CiscoCisco UCSC-GPU-V100-32 | Tesla V100 32GB HBM2 GPU, 5120 CUDA, 640 Tensor Cores
The Cisco UCSC-GPU-V100-32 is an enterprise-grade data center GPU accelerator powered by NVIDIA Volta architecture, designed for AI training, deep learning inference, and high-performance computing workloads. Featuring 32GB of HBM2 memory, 5120 CUDA cores, and 640 Tensor Cores, it delivers exceptional parallel processing performance with 900 GB/s memory bandwidth. This passive-cooled PCIe 3.0 x16 dual-slot GPU is optimized for deployment in Cisco UCS C-Series rack servers, providing the computational power needed for complex machine learning models, scientific simulations, and data analytics applications. -
Vendor:NVIDIA
NVIDIA 980-9I08S-00W050 | 400G QSFP-DD AOC | 850 nm MMF | 50 m | QSFP-DD to QSFP-DD
980-9I08S-00W050
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I08S-00W050 | 400G QSFP-DD AOC | 850 nm MMF | 50 m | QSFP-DD to QSFP-DD
High-bandwidth active optical cable for short-reach 400G interconnects. QSFP‑DD connectors on both ends deliver 8x50G PAM4 lanes over multimode fiber at 850 nm. Ideal for switch-to-switch or switch-to-adapter links where low weight, tight bend radius, and EMI immunity are required. Blue pull-tabs provide quick identification and easy extraction. -
Vendor:NVIDIA
NVIDIA 980-9I595-00AM00 | 25GbE SFP28 SR, 850nm, up to 70m (OM3)/100m (OM4), LC duplex
980-9I595-00AM00
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I595-00AM00 | 25GbE SFP28 SR, 850nm, up to 70m (OM3)/100m (OM4), LC duplex
Standards-based 25GbE SFP28 SR optical transceiver for short‑reach MMF links. Uses 850 nm VCSEL optics with LC duplex interface, supporting up to 70 m on OM3 or 100 m on OM4—ideal for top‑of‑rack to aggregation uplinks. Hot‑swappable and interoperable with IEEE 802.3by 25GBASE‑SR. -
Vendor:NVIDIA
NVIDIA 980-9I530-00W000 | Mellanox Select 400GbE QSFP-DD SR8 Transceiver
980-9I530-00W000
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I530-00W000 | Mellanox Select 400GbE QSFP-DD SR8 Transceiver
Pluggable optical transceiver for NVIDIA networking platforms. Use the platform bill of materials or compatibility matrix to confirm the exact form factor, data rate, optical standard, wavelength, reach, and connector for this part reference. -
Vendor:Cisco
Cisco UCSC-885A-M8-H27 | H200 GPU server | 8x ConnectX-7 | 2x BlueField-3 3220 | 3TB RAM
UCSC-885A-M8-H27
Stock Status: Enquire
Vendor:CiscoCisco UCSC-885A-M8-H27 | H200 GPU server | 8x ConnectX-7 | 2x BlueField-3 3220 | 3TB RAM
High-density rack server tailored for GPU-accelerated AI/ML and data analytics, combining H200 GPUs with high-performance networking and DPU offload. This build includes 8x ConnectX-7 and 2x BlueField-3 3220 for secure, accelerated data paths and massive parallel workloads, backed by 3TB of system memory. -
Vendor:NVIDIA
NVIDIA 980-9I13F-00C020 | InfiniBand AOC | 100G QSFP28 to QSFP28 | EDR/100GbE | 850nm | 20m | Integrated QSFP28 ends
980-9I13F-00C020
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I13F-00C020 | InfiniBand AOC | 100G QSFP28 to QSFP28 | EDR/100GbE | 850nm | 20m | Integrated QSFP28 ends
Active optical cable for 100G QSFP28 links supporting InfiniBand EDR and 100GbE over multimode fiber with integrated ends for simple, reliable deployment. Suited for extended intra-row runs up to 20 m. -
Vendor:NVIDIA
NVIDIA 980-9I58E-00N015 | MPO-12 OS2 SMF trunk, 15m, DR4/parallel single‑mode, yellow jacket
980-9I58E-00N015
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I58E-00N015 | MPO-12 OS2 SMF trunk, 15m, DR4/parallel single‑mode, yellow jacket
Single‑mode OS2 MPO-12 trunk for DR4/parallel optics interconnects in data center and HPC fabrics. 15 m run with Type‑B polarity, suitable for 100/200GbE DR4 and InfiniBand HDR links. -
Vendor:NVIDIA
NVIDIA 980-9I581-00N050 | MPO-12 trunk, SMF OS2, 60m, 1310nm PSM4/PLR4, MPO–MPO, yellow jacket
980-9I581-00N050
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I581-00N050 | MPO-12 trunk, SMF OS2, 60m, 1310nm PSM4/PLR4, MPO–MPO, yellow jacket
OS2 single‑mode MPO‑12 trunk for parallel optics, 60 m length for extended row or row‑to‑row interconnects. Supports 4‑lane PSM4/PLR4 100G links and parallel single‑mode applications. Factory‑terminated for consistent optical performance and simplified installation in high‑density environments. -
Vendor:Juniper
Juniper SRX650-BASESRE6-645DP | 4x 1G RJ45; 645W DC PoE PSU (247W PoE budget); NGFW/UTM; SD-WAN capable; LTE optional; license: base
SRX650-BASESRE6-645DP
Stock Status: Enquire
Vendor:JuniperJuniper SRX650-BASESRE6-645DP | 4x 1G RJ45; 645W DC PoE PSU (247W PoE budget); NGFW/UTM; SD-WAN capable; LTE optional; license: base
Branch/perimeter services gateway with SRE 6 compute, four onboard 10/100/1000BASE‑T ports, and a DC PoE power supply delivering a 247 W PoE budget for supported PoE modules. Designed for telco and industrial racks requiring DC input. -
Vendor:NVIDIA
NVIDIA 980-9I554-00N010 | Optics: 40/100/200G SR4‑ready, OM4 MMF, 850nm, 10m, MPO12–MPO12
980-9I554-00N010
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I554-00N010 | Optics: 40/100/200G SR4‑ready, OM4 MMF, 850nm, 10m, MPO12–MPO12
High‑performance MPO‑12 multimode OM4 trunk/patch cable for SR4 optics across 10 m runs. Ideal for QSFP+/QSFP28/QSFP56 SR4 links in high‑density leaf‑spine and aggregation networks. -
Vendor:Arista
Arista DCS-7060DX5-64S-R | 7060X5 64-Port 400G Switch, 25.6Tbps, 2RU
DCS-7060DX5-64S-R
Stock Status: Enquire
Vendor:AristaArista DCS-7060DX5-64S-R | 7060X5 64-Port 400G Switch, 25.6Tbps, 2RU
The Arista DCS-7060DX5-64S-R is a high-density data center switch delivering 64x 400GbE QSFP-DD ports in a 2RU form factor with 25.6 Tbps total throughput. Designed for spine/leaf architectures and AI/ML clusters, it supports flexible port speeds including 400G, 200G, and 100G with up to 256 interfaces via breakout. Powered by Arista EOS, this switch features ultra-low latency of 825ns, 114MB packet buffer, wire-speed Layer 2/Layer 3 forwarding, and advanced automation capabilities. The -R suffix indicates rear-to-front airflow with redundant hot-swappable AC power supplies. -
Vendor:Juniper
Juniper CTP150-CBL-DB15-DTE-M | HD-26 to DB15 interface cable | DTE, male DB15 | for CTP150
CTP150-CBL-DB15-DTE-M
Stock Status: Enquire
Vendor:JuniperJuniper CTP150-CBL-DB15-DTE-M | HD-26 to DB15 interface cable | DTE, male DB15 | for CTP150
Interface cable for CTP150 ports that adapts HD-26 to DB15 with DTE orientation and a male DB15 connector, enabling clean connectivity to devices requiring a DTE-ended DB15. -
Vendor:Juniper
Juniper CTP2000-RAM-UPG | Juniper CTP2000-RAM-UPG CTP2000 line upgrade kit for release 6.0 includes 1G RAM and 4G CompactFlash card.
CTP2000-RAM-UPG
Stock Status: Enquire
Vendor:JuniperJuniper CTP2000-RAM-UPG | Juniper CTP2000-RAM-UPG CTP2000 line upgrade kit for release 6.0 includes 1G RAM and 4G CompactFlash card.
All products sold by XS Network Tech include a 12-month warranty on both new and used items. Our in-house technical team thoroughly tests used hardware prior to sale to ensure enterprise-grade reliability. -
Vendor:Juniper
Juniper SRX-GP-QUAD-T1-E1 | 4x T1/E1 GPIM | 1.544/2.048 Mb/s | RJ-48C | SRX650 single-slot
SRX-GP-QUAD-T1-E1
Stock Status: Enquire
Vendor:JuniperJuniper SRX-GP-QUAD-T1-E1 | 4x T1/E1 GPIM | 1.544/2.048 Mb/s | RJ-48C | SRX650 single-slot
Quad-port T1/E1 GPIM for branch WAN connectivity on SRX650. Provides four configurable T1/E1 interfaces in a single GPIM slot for legacy carrier handoffs and voice/data backhaul.
