650 Search Results for "nvidia connectx-6"
-
Vendor:NVIDIA
NVIDIA MFS1S00-H050V | 200G QSFP56 AOC | IB HDR | 850nm MMF | 50m | QSFP56↔QSFP56
MFS1S00-H050V
Stock Status: Enquire
Vendor:NVIDIANVIDIA MFS1S00-H050V | 200G QSFP56 AOC | IB HDR | 850nm MMF | 50m | QSFP56↔QSFP56
200 Gb/s InfiniBand HDR active optical cable with integrated QSFP56 modules for long, lightweight data center interconnects. The 50 m reach enables cross-row and aggregation connectivity while maintaining low BER and latency. Perfect for AI/HPC fabrics and storage backbones needing clean 200G links without separate optics. Plug-and-play into QSFP56 HDR ports. -
Vendor:NVIDIA
NVIDIA MMA1L30-CM | 100G QSFP28 | 100G CWDM4 MSA | 1310nm CWDM4 | 2km SMF | LC duplex
MMA1L30-CM
Stock Status: Enquire
Vendor:NVIDIANVIDIA MMA1L30-CM | 100G QSFP28 | 100G CWDM4 MSA | 1310nm CWDM4 | 2km SMF | LC duplex
Cost‑effective 100G QSFP28 CWDM4 optical transceiver for 2 km single‑mode links. Utilizes four CWDM wavelengths (1271–1331 nm) over LC duplex to balance reach and power for campus and data center interconnects. -
Vendor:Blue Cable Co
MFM1T02A-SR-BCC | NVIDIA Mellanox Compatible 10GB Multi-Mode SFP+ 400m (10GBASE-SR)
MFM1T02A-SR-BCC
In stock
Vendor:Blue Cable CoMFM1T02A-SR-BCC | NVIDIA Mellanox Compatible 10GB Multi-Mode SFP+ 400m (10GBASE-SR)
The MFM1T02A-SR-BCC is a Blue Cable Co 10GbE 10GBASE-SR multi-mode SFP+ optical transceiver, compatible with NVIDIA Mellanox platforms. Operating at 850nm with a duplex LC connector, it delivers up to 300m on OM3 fibre and up to 400m on OM4 fibre at 10Gb/s. This plug-and-play module includes SFF-8472 compliant digital diagnostic monitoring (DDM) and is tested in our state-of-the-art lab in Sydney, Australia to ensure NVIDIA Mellanox platform compatibility. Every unit is backed by Blue Cable Co's 5-year advanced hardware replacement warranty.
- Plug-and-play SFP+ form factor — no additional configuration required
- IEEE 802.3ae 10GBASE-SR compliant, up to 10.3125 Gb/s data rate
- 850nm wavelength over multi-mode fibre with duplex LC connector
- Up to 300m on OM3 MMF; up to 400m on OM4 MMF at 10Gb/s (per datasheet, depends on fibre and link conditions)
- SFF-8472 compliant digital diagnostic monitoring (DDM) for real-time performance visibility
- Hot-pluggable design for live insertion without system downtime
- Operating case temperature range: 0°C to +70°C
- Maximum power consumption: 1W
- RoHS compliant and Class 1 laser safe
- Tested in Blue Cable Co's Sydney lab for NVIDIA Mellanox platform compatibility
- Backed by Blue Cable Co's 5-year advanced hardware replacement warranty
-
Vendor:NVIDIA
NVIDIA 980-9I58H-00N050 | IB/Ethernet MPO-12 SMF (OS2) trunk | 1310 nm | PSM4 40/100G-ready | 50 m | MPO–MPO | Yellow
980-9I58H-00N050
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I58H-00N050 | IB/Ethernet MPO-12 SMF (OS2) trunk | 1310 nm | PSM4 40/100G-ready | 50 m | MPO–MPO | Yellow
Single-mode MPO-12 trunk cable designed for high-density InfiniBand and Ethernet fabrics. Using OS2 (9/125 µm) fiber optimized for the 1310 nm window, it supports PSM4-style links for 40/100G deployments, delivering low loss and consistent performance across 50 meters. Ideal for connecting spine–leaf switches or HPC nodes where MPO-12 connectivity is required. -
Vendor:Cisco
Cisco UCSC-885A-M8-H11 | AI training server | 8x H100 GPUs | 8x ConnectX-7 | BlueField-3 DPU | 23TB memory
UCSC-885A-M8-H11
Stock Status: Enquire
Vendor:CiscoCisco UCSC-885A-M8-H11 | AI training server | 8x H100 GPUs | 8x ConnectX-7 | BlueField-3 DPU | 23TB memory
High-performance rack server configuration built for large-scale AI training and inference. Equipped with 8x NVIDIA H100 GPUs, 8x ConnectX-7 network adapters for high-throughput fabric connectivity, a BlueField-3 DPU for accelerated networking and security offload, and 23TB system memory for massive in-memory datasets. Ideal for LLM training, HPC, and advanced analytics workloads. -
Vendor:NVIDIA
NVIDIA MFS1S00-H150V | AOC | 200Gb/s IB HDR | QSFP56 | 850nm MMF | 150m | QSFP56
MFS1S00-H150V
Stock Status: Enquire
Vendor:NVIDIANVIDIA MFS1S00-H150V | AOC | 200Gb/s IB HDR | QSFP56 | 850nm MMF | 150m | QSFP56
QSFP56 active optical cable designed for 200Gb/s InfiniBand HDR backbones, offering extended 150m reach over multimode fiber with low latency and simplified deployment. Ideal for leaf–spine and storage interconnects where long, lightweight cabling is preferred. -
Vendor:Cisco
Cisco UCSC-GPU-L40 | L40 GPU 48GB GDDR6, 300W, PCIe Gen4, 2-Slot FHFL
UCSC-GPU-L40
Stock Status: Enquire
Vendor:CiscoCisco UCSC-GPU-L40 | L40 GPU 48GB GDDR6, 300W, PCIe Gen4, 2-Slot FHFL
The Cisco UCSC-GPU-L40 is an NVIDIA L40 GPU accelerator designed for enterprise data center deployments requiring visual computing, AI inference, and virtualized graphics workloads. Built on the Ada Lovelace architecture, this 300W, 2-slot full-height full-length card delivers 48GB of GDDR6 ECC memory with 864GB/s bandwidth, 18,176 CUDA cores, and 90.5 TFLOPS of FP32 performance. Ideal for virtual workstations, real-time ray tracing, 3D rendering, video encoding with AV1 support, and AI-driven applications in Cisco UCS C-Series rack servers. -
Vendor:NVIDIA
NVIDIA MCP7H50-H01AR30 | Passive copper breakout DAC | IB HDR 200G to 2x100G | QSFP56 to 2x QSFP56 | 1.5m
MCP7H50-H01AR30
Stock Status: Enquire
Vendor:NVIDIANVIDIA MCP7H50-H01AR30 | Passive copper breakout DAC | IB HDR 200G to 2x100G | QSFP56 to 2x QSFP56 | 1.5m
Mid-length passive copper HDR breakout cable that converts one 200G QSFP56 port into two 100G QSFP56 links. Ideal for low-latency fan-out connections within or between adjacent racks without added power or optics. -
Vendor:NVIDIA
NVIDIA MMS1W50-HM | 200Gb/s QSFP56 HDR FR4 1310nm 2km LC duplex
MMS1W50-HM
Stock Status: Enquire
Vendor:NVIDIANVIDIA MMS1W50-HM | 200Gb/s QSFP56 HDR FR4 1310nm 2km LC duplex
InfiniBand HDR 200G QSFP56 FR4 optical transceiver for long-reach single‑mode links. Uses 1310 nm CWDM4 wavelengths over LC duplex to extend up to 2 km on OS2 for HDR switch and adapter interconnects. -
Vendor:NVIDIA
NVIDIA MFP7E30-N060 | SMF MPO-12 APC to MPO-12 APC Trunk Cable, OFNR, Yellow, 60m
MFP7E30-N060
Stock Status: Enquire
Vendor:NVIDIANVIDIA MFP7E30-N060 | SMF MPO-12 APC to MPO-12 APC Trunk Cable, OFNR, Yellow, 60m
High-density single-mode MPO trunk for parallel optics interconnects. MPO-12 APC connectors on both ends with riser-rated (OFNR) yellow jacket for structured cabling in data halls and equipment rooms. Ideal for linking leaf/spine or accelerator fabrics where MPO-based SMF links are required. -
Vendor:NVIDIA
NVIDIA 980-9I50E-00N005 | 800G OSFP to 4x OSFP AOC | InfiniBand NDR/400GbE | MMF 850nm | 5 m | OSFP connectors
980-9I50E-00N005
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I50E-00N005 | 800G OSFP to 4x OSFP AOC | InfiniBand NDR/400GbE | MMF 850nm | 5 m | OSFP connectors
Active optical breakout cable enabling OSFP to 4x OSFP fan‑out for short‑reach data center and HPC links over 850nm multimode fiber. Extends high‑bandwidth fabrics with simple, integrated optics at 5 m reach. -
Vendor:NVIDIA
NVIDIA MFS1S50-H005V | Breakout AOC | 200G→2x100G IB HDR | QSFP56 to 2x QSFP56 | 850nm MMF | 5m
MFS1S50-H005V
Stock Status: Enquire
Vendor:NVIDIANVIDIA MFS1S50-H005V | Breakout AOC | 200G→2x100G IB HDR | QSFP56 to 2x QSFP56 | 850nm MMF | 5m
Compact breakout AOC that converts one 200Gb/s QSFP56 HDR uplink into two 100Gb/s QSFP56 connections for flexible topologies and efficient port utilization. Ideal for leaf–spine aggregation or server/NIC fanout with minimal cable bulk. -
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:Juniper
Juniper SRX-IOC-16GE-TX | SRX5000 Flex IOC | 16x 10/100/1000BASE-T RJ-45 | requires SRX5K-FPC-IOC | SRX5600/SRX5800
SRX-IOC-16GE-TX
Stock Status: Enquire
Vendor:JuniperJuniper SRX-IOC-16GE-TX | SRX5000 Flex IOC | 16x 10/100/1000BASE-T RJ-45 | requires SRX5K-FPC-IOC | SRX5600/SRX5800
Flex IOC module delivering 16 copper Gigabit Ethernet ports for SRX5000 line, ideal for high-density 1G RJ‑45 access on SRX5600/SRX5800. Installs into the SRX5K-FPC-IOC carrier. -
Vendor:NVIDIA
NVIDIA 980-9I57Y-00N050 | MMF MPO-12 APC trunk, 850nm SR4, Type-B, 50m, up to 200G, MPO-12 to MPO-12
980-9I57Y-00N050
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I57Y-00N050 | MMF MPO-12 APC trunk, 850nm SR4, Type-B, 50m, up to 200G, MPO-12 to MPO-12
Passive MPO-12 multimode trunk for SR4-based Ethernet and InfiniBand links. MPO-12 APC on both ends with Type-B polarity provides plug-and-play 40/100/200G connectivity for QSFP-SR4 and QSFP56-SR4 optics. Length: 50 m. -
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:NVIDIA
NVIDIA MFA7U10-H030 | 400G to 2x200G AOC | OSFP to 2xQSFP56 | IB HDR | 850nm | 30m | MMF
MFA7U10-H030
Stock Status: Enquire
Vendor:NVIDIANVIDIA MFA7U10-H030 | 400G to 2x200G AOC | OSFP to 2xQSFP56 | IB HDR | 850nm | 30m | MMF
Active optical splitter cable for InfiniBand HDR, breaking a 400G OSFP port into two 200G QSFP56 links over multimode fiber. Lightweight, low-power, and factory-terminated for reliable 30m rack-to-rack connectivity. -
Vendor:Cisco
Cisco UCSX-GPU-H100-NVL | H100 NVL PCIe Accelerator, 94GB HBM3, 400W, 2-Slot
UCSX-GPU-H100-NVL
Stock Status: Enquire
Vendor:CiscoCisco UCSX-GPU-H100-NVL | H100 NVL PCIe Accelerator, 94GB HBM3, 400W, 2-Slot
The Cisco UCSX-GPU-H100-NVL is an NVIDIA H100 NVL Tensor Core GPU designed for large language model inference, AI training, and high-performance computing workloads in enterprise data centers. Built on the Hopper architecture with 94GB of HBM3 memory and 3.9TB/s bandwidth, it delivers exceptional performance for transformer models and generative AI applications. The 2-slot FHFL form factor integrates into Cisco UCS X-Series servers with PCIe Gen5 connectivity. -
Vendor:Blue Cable Co
MMA1B00-B150D-BCC | NVIDIA Mellanox Compatible 40GB Multi-Mode QSFP+ 150m (40GBASE-SR4)
MMA1B00-B150D-BCC
In stock
Vendor:Blue Cable CoMMA1B00-B150D-BCC | NVIDIA Mellanox Compatible 40GB Multi-Mode QSFP+ 150m (40GBASE-SR4)
The MMA1B00-B150D-BCC is a Blue Cable Co 40GbE 40GBASE-SR4 multi-mode QSFP+ optical transceiver, compatible with NVIDIA Mellanox platforms. Operating at 850nm across four parallel channels via an MPO connector, it supports up to 150m on OM4 fibre and up to 100m on OM3 fibre at 40Gb/s. This plug-and-play module includes digital diagnostic monitoring (DDM) covering temperature, voltage, and optical power levels, and is tested in our state-of-the-art lab in Sydney, Australia to ensure NVIDIA Mellanox platform compatibility. Stocked and shipped from Sydney, Australia, and backed by Blue Cable Co's 5-year advanced hardware replacement warranty.
- Plug-and-play QSFP+ form factor — no additional configuration required
- IEEE 802.3 40GBASE-SR4 compliant, 40Gb/s via 4x10.3125Gb/s parallel channels
- 850nm VCSEL transmitter over parallel multi-mode fibre with MPO connector
- Up to 150m on OM4 MMF; up to 100m on OM3 MMF (per datasheet, depends on fibre and link conditions)
- Digital diagnostic monitoring (DDM) — covers supply voltage, temperature, Tx/Rx optical power, and VCSEL bias
- Hot-pluggable QSFP+ design for live insertion without system downtime
- Operating case temperature range: 0°C to +70°C
- Power dissipation: 1.3W typical, 1.5W maximum
- RoHS compliant and Class 1 laser safe
- Tested in Blue Cable Co's Sydney lab for NVIDIA Mellanox platform compatibility
- Stocked in Sydney, Australia for fast local dispatch
- Backed by Blue Cable Co's 5-year advanced hardware replacement warranty
-
Vendor:NVIDIA
NVIDIA 980-9I433-00N001 | Optics: 400G, OSFP AOC (FLAT), IB NDR/400GbE, 850nm, 1m, OSFP↔OSFP
980-9I433-00N001
Stock Status: Enquire
Vendor:NVIDIANVIDIA 980-9I433-00N001 | Optics: 400G, OSFP AOC (FLAT), IB NDR/400GbE, 850nm, 1m, OSFP↔OSFP
Flat‑jacket OSFP active optical cable designed for ultra‑dense routing and tight cable management in 400G fabrics. Delivers the same low‑power, EMI‑immune performance as standard AOCs with a low‑profile, lay‑flat construction that eases dressing through congested pathways and narrow rack gaps. -
Vendor:NVIDIA
NVIDIA MFS1S00-H020V | 200G QSFP56 AOC | IB HDR | 850nm MMF | 20m | QSFP56↔QSFP56
MFS1S00-H020V
Stock Status: Enquire
Vendor:NVIDIANVIDIA MFS1S00-H020V | 200G QSFP56 AOC | IB HDR | 850nm MMF | 20m | QSFP56↔QSFP56
Active optical cable for 200 Gb/s InfiniBand HDR links with integrated QSFP56 connectors on both ends. Delivers high bandwidth and low latency over 20 meters while remaining lighter and more flexible than copper DAC. Ideal for AI/HPC clusters and leaf–spine fabrics where clean, deterministic performance is required. Plug-and-play with QSFP56 HDR switch/NIC ports; no separate transceivers needed. -
Vendor:Arista
Arista DCS-7060X6-64PE-B-F | 7060X6 64-Port 800G Data Center Switch, 51.2 Tbps, 2RU
DCS-7060X6-64PE-B-F
Stock Status: Enquire
Vendor:AristaArista DCS-7060X6-64PE-B-F | 7060X6 64-Port 800G Data Center Switch, 51.2 Tbps, 2RU
The Arista DCS-7060X6-64PE-B-F is a high-density 800G data center switch delivering 64 OSFP ports and 51.2 Tbps non-blocking switching capacity in a 2RU form factor. Engineered for AI/ML clusters, hyperscale leaf-spine architectures, and high-performance storage networks, it features 165 MB shared packet buffer, 700 ns ultra-low latency, and a field-replaceable supervisor card for extended platform lifecycle. Powered by Arista EOS, it supports dynamic buffer allocation, advanced DCQCN for lossless Ethernet, and flexible breakout configurations down to 100G. -
Vendor:Juniper
Juniper SRX600-SRE6H | SRE6-H services engine | SRX650 control/services module | FRU
SRX600-SRE6H
Stock Status: Enquire
Vendor:JuniperJuniper SRX600-SRE6H | SRE6-H services engine | SRX650 control/services module | FRU
Spare SRE6-H Services and Routing Engine module for SRX650. Restores or expands control and services processing capability within the SRX650 platform. Ideal as a replacement FRU to recover from hardware failures or to keep as onsite spares for rapid recovery. -
Vendor:NVIDIA
NVIDIA MCP7H50-H001R30 | Passive copper breakout DAC | IB HDR 200G to 2x100G | QSFP56 to 2x QSFP56 | 1m
MCP7H50-H001R30
Stock Status: Enquire
Vendor:NVIDIANVIDIA MCP7H50-H001R30 | Passive copper breakout DAC | IB HDR 200G to 2x100G | QSFP56 to 2x QSFP56 | 1m
Passive copper HDR breakout cable for splitting a single 200G QSFP56 port into two 100G QSFP56 links. Ideal for aggregating or fanning out HDR ports with the lowest latency and zero power consumption.
