Full English Description for Cisco N9K-C9348D-GX2A

1. Part Number Naming Breakdown

Model: N9K-C9348D-GX2A

N9K: Cisco Nexus 9000 cloud-scale fixed data center switch family
C9348D: High-density 2RU fixed chassis with 48 × QSFP-DD universal high-speed ports plus 2 auxiliary SFP+ ports
D: QSFP-DD dual-density optical interface, native 400G, full multi-speed breakout capability
GX2: Second-generation GX Cloud Scale ASIC with 120MB shared packet buffer, doubled L2/L3 TCAM scale, optimized RoCEv2 lossless transport for AI/HPC workloads
A: Standard ACI factory pre-configured port profile variant, default leaf port partitioning, optimized APIC discovery and streamlined POAP zero-touch automation workflows, dual operating modes: standalone NX-OS and ACI intent-based fabric mode

2. Short Sales One-Liner (For BOM, Quotation & Datasheet Header)

Cisco Nexus N9K-C9348D-GX2A, 2RU rack-mount ultra-high-density dual-purpose 400G leaf/spine data center switch, 48 universal breakout-capable QSFP-DD 400G/200G/100G/40G ports plus 2 × 1/10G SFP+ auxiliary downlink ports, 38.4 Tbps full non-blocking switching capacity, dual hot-swappable 3200W Platinum-efficiency redundant power supplies and eight 7+1 N+1 variable-speed fan trays, dual-mode standalone NX-OS or native ACI fabric operation, purpose-built for hyperscale leaf-spine core spine interconnection, large AI/GPU training clusters, low-latency HPC parallel computing, multi-pod ACI fabrics and 400G unified converged storage-compute deploymentsCisco.

3. Complete Product Overview Paragraph

The Cisco Nexus N9K-C9348D-GX2A is a high-density 2RU fixed-port Layer 2/3 all-optical flexible leaf/spine switch built on the second-gen GX Cloud Scale ASIC, a factory ACI-tuned platform optimized for both top-of-rack 400G leaf aggregation and core fabric spine roles in enterprise, hyperscale cloud, AI/ML training, HPC and Cisco ACI Application Centric Infrastructure multi-pod environments. It delivers industry-leading port density with 48 universal QSFP-DD high-speed optical ports paired with two auxiliary 1/10G SFP+ ports for low-speed management or secondary server downlinks, supporting full wire-rate non-blocking forwarding with total switching bandwidth of 38.4 Tbps and forwarding throughput of 8.35 Bpps for minimum 64-byte Ethernet framesCisco.

All 48 QSFP-DD ports support native 400G, backward-compatible 200G (QSFP56), 100G (QSFP28) and 40G (QSFP+) transceivers, plus full independent breakout configurations per port: 2×200G, 4×100G, 4×50G, 4×25G, 4×10G, enabling flexible logical port scaling up to 192 × 100G logical links within one 2RU chassis. Every QSFP-DD port supports wire-rate 128/256-bit MACsec & CloudSec encryption to secure all fabric inter-switch links without external security appliancesCisco. The two SFP+ auxiliary ports operate at auto-negotiated 1G/10G for auxiliary server, backup storage or secondary management access.

Powered by GX2-series Cloud Scale silicon, this platform features a massive 120MB shared dynamic packet buffer to absorb heavy burst traffic from parallel GPU training workloads, drastically expanded MAC address table, ultra-large IPv4/IPv6 LPM TCAM route scale, native hardware acceleration for EVPN/VXLAN overlay routing, and deeply optimized RoCEv2 lossless congestion control for ultra-low-latency AI training clusters. High-performance unsampled streaming telemetry integrates fully with Cisco Tetration Analytics for end-to-end full-fabric observability, alongside expanded VRF, multicast and microsegmentation policy capacity for multi-tenant hyperscale isolation. As the GX2A ACI-standard variant, it ships with factory preloaded ACI leaf port profiles: default leaf partition assigns ports 1–36 as server downlinks and ports 37–48 as inter-spine fabric uplinks, with accelerated APIC controller discovery and streamlined POAP zero-touch provisioning to reduce ACI fabric deployment time.

The chassis integrates dual independent out-of-band management interfaces: dedicated 10/100/1000BASE-T RJ45 Ethernet and SFP multi-rate fiber remote management uplink ports, plus mini-USB RS232 local console and single USB 2.0 Type-A port to support offline configuration backup and firmware upgrades. Dual hot-swappable 3200W power supplies and eight N+1 redundant fan trays eliminate single points of hardware failure, with two standardized airflow variants (PI port-side intake / PE port-side exhaust) selectable at order time; all power and fan modules must match airflow direction during operation to avoid thermal overload. This switch supports two independent operating modes: modular standalone Cisco NX-OS for traditional routed core/leaf data center architectures, or native ACI fabric mode for policy-driven automated multi-tenant cloud infrastructure. Its high-density 2RU 400G flexible dual-purpose design maximizes rack port density for mixed leaf/spine terabit-scale fabric deployments and modern large-scale AI GPU workload racks.

4. Detailed Hardware Interface Specifications

Universal QSFP-DD High-Speed Ports (48 × Full Breakout Multi-Rate Slots, all MACsec-capable)

Native supported line rates: 400GBASE, 200G QSFP56, 100G QSFP28, 40G QSFP+
Per-port breakout options: 2×200G, 4×100G, 4×50G, 4×25G, 4×10G via breakout cables & QSA adapters
MACsec capability: All 48 QSFP-DD ports support wire-rate 128/256-bit MACsec & CloudSec encryption
Compatible transceivers: QSFP-DD 400G DR4/FR4/LR4/ZR, QSFP56 200G, QSFP28 100G, QSFP+ 40G, passive QSFP-DD DAC twinax cables
ACI default port mapping: Ports 1–36 = leaf downlinks; Ports 37–48 = fabric uplinks reserved for APIC discovery and inter-pod connectivity

Auxiliary SFP+ Ports (2 × Auto-Sensing 1/10G Slots)

Auto-negotiated speeds: 1 Gbps, 10 Gbps
Use cases: Auxiliary low-speed server downlinks, secondary storage access, backup management links

Management & Auxiliary Ports

1 × 10/100/1000BASE-T RJ45 out-of-band management port
1 × SFP multi-rate fiber remote out-of-band management uplink port
1 × Mini-USB RS232 console port for local CLI access
1 × USB 2.0 Type-A port for firmware upload, configuration backup and POAP deployment

Power & Cooling

Dual hot-swappable power supply options (1+1 load-sharing redundancy, non-disruptive hot-swap):

3200W AC PI (port intake), 3200W AC PE (port exhaust), 3200W DC PI, 3200W HVDC PI/PE
Eight variable-speed fan trays (7+1 N+1 redundancy):

NXA-SFAN-PI (burgundy label, port-side intake)

NXA-SFAN-PE (blue label, port-side exhaust)
Power efficiency: 80Plus Platinum certified
Operating temperature range: 0°C ~ 40°C full load; non-operating storage: -40°C ~ 70°C
Humidity tolerance: 5%–95% non-condensing operating; max operating altitude: 4000 metersCisco

Physical Form Factor

Dimensions: 2RU standard 19-inch rack chassis

Height: 8.7 cm, Width: 44.1 cm, Depth: 76.1 cm fully populated
Weight: 16.8 kg empty chassis (no PSUs/fans); fully populated weight ~22.5 kg
Compliance: RoHS-6, NEBS Level 3, global safety, EMC and telecom regulatory certifications
MTBF: 211,310 hours under standard operating conditionsCisco

Core Hardware Performance Benchmarks

Total switching capacity: 38.4 Tbps full duplex non-blocking
Forwarding rate: 8.35 Bpps (64-byte frame wire-rate)
Shared dynamic packet buffer: 120MB for cross-port burst traffic absorption
MAC address table size: Expanded GX2-scale large MAC forwarding entry pool
IPv4 / IPv6 unicast LPM route table capacity: Ultra-large TCAM scale for hyperscale multi-pod fabrics
VLAN support: Up to 4094 standard IEEE 802.1Q tagged VLANs
Maximum isolated VRF instances: 16,000 multi-tenant virtual routing tables
System memory: 32GB DRAM + 128GB high-capacity onboard SSD storage
Typical cut-through switching latency: Less than 1 microsecond for minimum-size Ethernet framesCisco

5. Core Software Feature Suite (Dual NX-OS / ACI Operating Modes)

Layer 2 & Layer 3 Routing

Static routing, RIP, OSPFv2/v3, EIGRP, full BGP routing suite, VRRP, PIM sparse/dense multicast; FCoE not supported on this pure high-speed optical chassis

Cloud Fabric Overlay

Hardware-accelerated EVPN/VXLAN symmetric & asymmetric routing, multi-tenant VXLAN segmentation, fabric multicast optimization, advanced lossless RoCEv2 congestion control optimized for GPU/AI/HPC low-latency training workload clusters

Enterprise & Fabric Security

802.1X port authentication, MAB MAC bypass authentication, DHCP Snooping, Dynamic ARP Inspection, CoPP control-plane policing, hardware wire-rate 128/256-bit MACsec + CloudSec encryption on all 48 QSFP-DD fabric ports, TrustSec SGT zero-trust micro-segmentation for core fabric isolation

Monitoring & Telemetry

High-performance sampled/unsampled IPFIX streaming telemetry, ERSPAN remote port mirroring, local SPAN/VSPAN, real-time per-port/per-queue buffer utilization visibility, full Cisco Tetration flow export compatibility for end-to-end fabric analytics

Exclusive GX2A ACI Standard Optimized Features

Factory predefined ACI leaf port partition profile (36 downlinks + 12 fabric uplinks), accelerated APIC controller discovery logic, streamlined ACI POAP zero-touch provisioning workflow, built-in inter-pod IPN link validation templates, preconfigured breakout port mapping for large-scale ACI multi-pod deployments

Automation & DevOps

POAP zero-touch provisioning, NX-API REST JSON/XML APIs, embedded Linux Bash shell, native Python scripting, Ansible/Puppet/Chef full integration, containerized application hosting, hot patching and ISSU in-service software upgrade without core fabric traffic downtime

High Availability

Modular fault-isolated process architecture, stateful process restart, redundant control plane, hot-swappable power supply and fan FRUs for non-disruptive field maintenance

6. Typical Deployment Use Cases

Dual-purpose flexible leaf or core spine switch for large-scale 100G/400G leaf-spine hyperscale data center fabrics
Ultra-high-density aggregation leaf switch for massive 400G GPU virtualization and large-scale AI model training clusters
Inter-pod border spine switch connecting multiple independent ACI multi-pod fabric domains
Dedicated high-bandwidth core node for hyperscale IaaS/PaaS multi-tenant cloud environments
Professional media network core switch for 4K/8K ultra-high-bitrate streaming and large media asset workloads
5G edge NFV aggregation switch supporting high-speed backhaul 100G/400G optical links
HPC parallel computing cluster leaf/spine with breakout capability to support mixed 25G/100G/400G GPU interconnect speeds

7. Datasheet Short Summary Paragraph

The Cisco Nexus N9K-C9348D-GX2A is a 2RU ACI-standard GX2-generation ultra-high-density flexible dual-purpose 400G leaf/spine cloud data center switch equipped with 48 breakout-capable universal QSFP-DD 400G/200G/100G fabric ports plus two auxiliary 1/10G SFP+ ports, delivering 38.4 Tbps non-blocking switching performance with dual 3200W Platinum redundant power and eight 7+1 redundant fan trays. Supporting both standalone modular NX-OS and native ACI intent-based fabric operational modes, it features the second-gen GX Cloud Scale ASIC with a large 120MB packet buffer, ultra-expanded L2/L3 TCAM routing scale, full-port wire-rate MACsec/CloudSec encryption and optimized RoCEv2 lossless transport, plus factory pre-tuned ACI automation profiles, serving as a high-port-density terabit leaf/spine aggregation switch for hyperscale cloud, AI/GPU HPC, multi-pod ACI fabrics and professional media/5G edge networking built around 100G/400G high-speed optical fabric infrastructure.


	© 2026 Kino Technology Limited. All Rights Reserved. \| Hong Kong Registered · Shenzhen Operation \| New & Genuine Used Network Equipment Supplier