-
Vendor:NVIDIA
NVIDIA 900-9D3D4-00EN-HA0 | 1x400G QSFP112 NDR InfiniBand, PCIe Gen5 x16, HHHL tall bracket
900-9D3D4-00EN-HA0
Vendor:NVIDIANVIDIA 900-9D3D4-00EN-HA0 | 1x400G QSFP112 NDR InfiniBand, PCIe Gen5 x16, HHHL tall bracket
BlueField-3 B3140H data processing unit with a single 400G NDR InfiniBand port for ultra‑low‑latency HPC and AI fabrics. QSFP112 interface enables 400G PAM4 connectivity over compatible NDR optics, AOCs, or DACs. Half-height, half-length card with tall bracket and PCIe Gen5 x16 host interface for maximum bandwidth to the server. Ideal for accelerating networking, storage, and security offloads in modern data centers. -
Vendor:NVIDIA
NVIDIA 900-9D3C6-00SV-DA0 | BlueField-3 B3220SH DPU | 2x200GbE/NDR200, 2xQSFP112, PCIe Gen5 x16, Tall Bracket
900-9D3C6-00SV-DA0
Vendor:NVIDIANVIDIA 900-9D3C6-00SV-DA0 | BlueField-3 B3220SH DPU | 2x200GbE/NDR200, 2xQSFP112, PCIe Gen5 x16, Tall Bracket
200G DPU with dual QSFP112 ports and PCIe Gen5 x16 for high-throughput Ethernet or NDR200 InfiniBand fabrics. Provides hardware offload for virtual switching, RDMA, NVMe-oF/TCP, and inline crypto to optimize CPU utilization and application latency. Supplied with a tall bracket for standard server slots. -
Vendor:NVIDIA
NVIDIA 900-9D3C6-00CV-DA0 | BlueField-3 B3220SH DPU | 2x200GbE/NDR200, 2xQSFP112, PCIe Gen5 x16, FHHL
900-9D3C6-00CV-DA0
Vendor:NVIDIANVIDIA 900-9D3C6-00CV-DA0 | BlueField-3 B3220SH DPU | 2x200GbE/NDR200, 2xQSFP112, PCIe Gen5 x16, FHHL
200G BlueField-3 DPU variant with dual QSFP112 ports supporting 200GbE or NDR200 InfiniBand. PCIe Gen5 x16 delivers headroom for AI/ML fabrics, cloud networking, and accelerated storage, while onboard engines offload OVS, RoCE v2, NVMe-oF/TCP, and IPsec/TLS to reduce CPU load and latency. -
Vendor:NVIDIA
NVIDIA 900-9D3B6-00SV-AA0 | BlueField-3 B3220 DPU | 2x200GbE/NDR200, 2xQSFP112, PCIe Gen5 x16, Tall Bracket
900-9D3B6-00SV-AA0
Vendor:NVIDIANVIDIA 900-9D3B6-00SV-AA0 | BlueField-3 B3220 DPU | 2x200GbE/NDR200, 2xQSFP112, PCIe Gen5 x16, Tall Bracket
High-performance 200G DPU with dual-mode Ethernet/NDR200 InfiniBand ports via QSFP112. PCIe Gen5 x16 host interface feeds demanding workloads while inline acceleration offloads OVS, RoCE v2, NVMe-oF/TCP, and IPsec/TLS. Designed for secure, multi-tenant cloud, AI/ML fabrics, and ultra-low-latency storage networking. -
Vendor:NVIDIA
NVIDIA 900-9D3B6-00SC-EA0 | BlueField-3 B3210E DPU | 2x100GbE/HDR100, 2xQSFP56, PCIe x16, FHHL
900-9D3B6-00SC-EA0
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 900-9D3B6-00CV-AA0 | Dual QSFP112 200GbE/NDR200 IB DPU, PCIe Gen5 x16, FHHL (Tall Bracket)
900-9D3B6-00CV-AA0
Vendor:NVIDIANVIDIA 900-9D3B6-00CV-AA0 | Dual QSFP112 200GbE/NDR200 IB DPU, PCIe Gen5 x16, FHHL (Tall Bracket)
FHHL DPU with dual QSFP112 ports delivering 200GbE Ethernet (default) or NDR200 InfiniBand, featuring PCIe Gen5 x16 for maximum host bandwidth and low-latency acceleration. -
Vendor:NVIDIA
NVIDIA 900-9D3B6-00CC-EA0 | Dual-port 100GbE/HDR100 IB DPU, FHHL, PCIe Gen5, E‑Series
900-9D3B6-00CC-EA0
Vendor:NVIDIANVIDIA 900-9D3B6-00CC-EA0 | Dual-port 100GbE/HDR100 IB DPU, FHHL, PCIe Gen5, E‑Series
E‑Series FHHL DPU offering dual 100GbE Ethernet (default) or HDR100 InfiniBand connectivity, bringing acceleration for secure networking, virtualization, and storage workloads. -
Vendor:NVIDIA
NVIDIA 900-9D3B4-00SV-EA0 | Dual-port 200GbE/NDR200 IB SuperNIC, FHHL, PCIe Gen5, E‑Series
900-9D3B4-00SV-EA0
Vendor:NVIDIANVIDIA 900-9D3B4-00SV-EA0 | Dual-port 200GbE/NDR200 IB SuperNIC, FHHL, PCIe Gen5, E‑Series
E‑Series FHHL SuperNIC delivering dual 200GbE Ethernet (default) or NDR200 InfiniBand for high‑performance data center fabrics, enabling low latency and high throughput with advanced acceleration. -
Vendor:NVIDIA
NVIDIA 900-9D3B4-00CV-EA0 | Dual-port 200GbE/NDR200 IB SuperNIC, FHHL, PCIe Gen5, E‑Series
900-9D3B4-00CV-EA0
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 900-83668-0030-000 | Xavier NX 16GB Dev Kit | 6-core Carmel, 384-core Volta + 48 Tensor | 16GB LPDDR4x | microSD boot, M.2 NVMe | GbE, 4x USB, HDMI/DP | up to 21 TOPS
Enhanced memory variant of the edge AI development kit for larger models and higher-resolution vision workloads. Combines a 6-core Carmel CPU with a 384-core Volta GPU and 48 Tensor Cores, plus NVMe expansion and camera-rich I/O for demanding robotics and analytics. -
Vendor:NVIDIA
NVIDIA 900-83668-0000-000 | Xavier NX Dev Kit | 6-core Carmel, 384-core Volta + 48 Tensor | 8GB LPDDR4x | microSD boot, M.2 NVMe | GbE, 4x USB, HDMI/DP | up to 21 TOPS
High-performance edge AI development kit delivering up to 21 TOPS for real-time vision, robotics, and multimodal inference. Combines a 6-core Carmel CPU with a 384-core Volta GPU and 48 Tensor Cores, plus rich I/O and NVMe expansion on a compact carrier. -
Vendor:NVIDIA
NVIDIA 900-83489-0080-000 | TX2 4GB Module | 2x Denver 2 + 4x A57, 256-core Pascal | 4GB LPDDR4, eMMC 5.1 | 4K codec | JetPack-ready
900-83489-0080-000
Vendor:NVIDIANVIDIA 900-83489-0080-000 | TX2 4GB Module | 2x Denver 2 + 4x A57, 256-core Pascal | 4GB LPDDR4, eMMC 5.1 | 4K codec | JetPack-ready
Compact edge AI module combining a heterogeneous 6-core CPU with a 256-core Pascal GPU for accelerated computer vision and inference in space- and power-constrained designs. Drop-in compatible with TX2 ecosystem carriers and JetPack software. -
Vendor:NVIDIA
NVIDIA 900-83489-0000-000 | TX2i Dev Kit | 2x Denver 2 + 4x A57 CPU, 256-core Pascal GPU | 8GB LPDDR4, eMMC 5.1 | GbE, USB 3.0, CSI, HDMI | JetPack-ready
Industrial-ready edge AI development platform based on a heterogeneous 6-core CPU and 256-core Pascal GPU. Ideal for prototyping computer vision, robotics, and smart sensors with rich I/O and camera interfaces on a compact carrier. Deploy with JetPack for accelerated CUDA, cuDNN, and TensorRT workflows. -
Vendor:NVIDIA
NVIDIA 900-83310-0001-000 | TX2 8GB Module | 6-core ARMv8 (2x Denver2 + 4x A57), Pascal 256-core GPU, 8GB LPDDR4, 32GB eMMC, MIPI CSI-2, PCIe, GbE
Compact edge AI module delivering balanced performance and power efficiency for vision, robotics, and embedded AI. Combines a 6-core heterogeneous ARMv8 CPU with a 256-core Pascal GPU and onboard storage for production deployments. -
Vendor:NVIDIA
NVIDIA 900-82888-0080-000 | AGX Xavier Industrial Module | 8-core ARMv8 (Carmel), Volta 512-core GPU + 64 Tensor Cores, 32GB LPDDR4x, 32GB eMMC, extended-temp, MIPI CSI-2, PCIe, GbE
Ruggedized AGX Xavier system-on-module designed for harsh environments and long-life deployments. Delivers high-performance edge AI with an 8-core ARMv8 CPU, Volta GPU with Tensor Cores, and industrial-focused reliability features. -
Vendor:NVIDIA
NVIDIA 900-82888-0050-000 | AGX Xavier Dev Kit (64GB) | 8-core ARMv8 (Carmel), Volta 512-core GPU + 64 Tensor Cores, 32GB LPDDR4x, 64GB eMMC, GbE, USB 3.1, M.2 NVMe, MIPI CSI-2, HDMI/DP
Enhanced AGX Xavier developer platform featuring 64GB onboard eMMC for larger datasets and applications. Combines an 8-core ARMv8 CPU and Volta GPU with Tensor Cores, plus comprehensive I/O for rapid edge AI prototyping.
-
Why buy NVIDIA from XS Network Tech?
Trusted by data centres and AI infrastructure teams across Australia, XS Network Tech delivers NVIDIA networking hardware with the speed and precision high-throughput environments demand. Our expert sales team supports pre-sales specification for GPU fabrics and AI builds, with local Sydney stock available for same-day dispatch. Wide inventory across current and EOL NVIDIA platforms, every used unit tested and backed by a 12-month warranty.
-
Can I buy used NVIDIA networking hardware in Australia?
Yes. We stock new, used, and EOL NVIDIA networking equipment locally in our Sydney warehouse for fast Australia-wide dispatch. Used NVIDIA hardware is a cost-effective option for teams building out AI infrastructure or high-throughput data centre fabrics without new-hardware lead times or pricing. We also offer configure-to-order NVIDIA GPU servers. Spec your CPU, memory, storage, and networking to match your exact workload, and we'll build and test it before despatch.
-
What NVIDIA products does XS Network Tech stock?
Our NVIDIA range spans ConnectX SmartNICs (ConnectX-6, ConnectX-7), Spectrum Ethernet switches (SN4600, SN4700), DAC and AOC cables (MCP, MFS series), Quantum InfiniBand switches, and GPU compute including RTX A-series, RTX 4000/6000 Ada, and RTX Blackwell, plus BlueField DPUs and Jetson edge AI modules. Can't find your model? Get in touch and we will sort it.