A high-tech enterprise specializing in the research and development of optical fiber communications and manufacturing.
Language
A high-tech enterprise specializing in the research and development of optical fiber communications and manufacturing.
The KEXINT Mellanox MQM9790-NS2F is a premier 1U unmanaged InfiniBand data center switch based on the cutting-edge NVIDIA Quantum™-2 platform. Engineered to meet the extreme networking demands of modern artificial intelligence (AI), machine learning (ML), and high-performance computing (HPC) clusters, this enterprise-grade switch delivers an unprecedented 64 ports of NDR 400Gb/s InfiniBand with a staggering aggregate bidirectional throughput of 51.2Tb/s.
Featuring 32 physical 800Gb OSFP interfaces that seamlessly split to support high-density fiber connections, the MQM9790-NS2F ensures ultra-low latency, optimal power-to-connector (P2C) airflow, and massive bandwidth scaling. As a globally trusted B2B optical network solution provider, KEXINT guarantees outstanding performance, 100% rigorous product testing, and professional technical support. Elevate your next-generation data center infrastructure with the industry-leading speed, reliability, and efficiency of the MQM9790-NS2F.
Product Description
MQM9790-NS2F, NVIDIA® 64-Port NDR 400G InfiniBand Data Center Switch, 32 x 800Gb OSFP, Unmanaged, x86 Dual Core, NVIDIA Quantum™-2 Chip
The NVIDIA Quantum-2-based MQM9790-NS2F switch comes with 64 400Gb/s ports on 32 physical octal small form-factor pluggable (OSFP) connectors that can be split to deliver up to 128 200Gb/s ports in a 1U standard chassis design. This switch use connector cages that house two 400Gb/s ports in a single cage called 2x400G (800G) twin-port OSFP and are used exclusively in these air-cooled switches. A single switch carries an aggregated bidirectional throughput of 51.2 terabits per second (Tb/s), with a landmark of more than 66.5 billion packets per second (BPPS) capacity.
Supporting the latest NVIDIA high-speed interconnect 400Gb/s technology, NVIDIA Quantum-2 brings a high-speed, extremely low-latency and scalable solution that incorporates state-of-the-art technologies such as Remote Direct Memory Access (RDMA), adaptive routing, and NVIDIA Scalable Hierarchical Aggregation and Reduction Protocol (SHARP)™.
Product Highlights
32 OSFP Ports, Can Use Breakout for 64× 400GbE or 128× 200GbE
25.6 Tb/s Aggregate Switch Throughput, More Than 66.5 Billion Packets per Second
1+1 Hot-swappable Power Supplies, 6+1 Hot-swappable Fans
Support SHARPV3, Adaptive Routing, Congestion Control and QoS, Self-healing Networking
Support Fat Tree, SlimFly, Dragonfly+, Multi-dimensional and Other Network Topologies
Support UFM® Platform for Flexible Operation
Specifications
| Manufacturer | Mellanox | Ports | 64 x NDR 400G 32 OSFP Connectors |
| CPU | x86 Coffee Lake i3 | Switch Chip | NVIDIA QUANTUM-2 |
| Software | MLNX-OS | Switching Capacity | 25.6 Tbps |
| Typical Power Consumption | 640W | System Memory | Single 8GB |
| Max. Power Consumption | 1593W | Storage | M.2 SSD SATA 16GB 2242 FF |
| AC Power Supplies | 1+1 Hot-swappable | Voltage | 1x/2x, 200-240VAC 50/60Hz 10A |
| Fan Number | 6+1 Hot-swappable | Airflow | Back-to-Front（P2C） |
| Operating Temperature | 32°F to 95°F (0° to 35°C) | Storage Temperature | -40°F to 158°F (-40ºC to 70ºC) |
| Dimensions (Hx Wx D) | 1.7"x 17"x 26"(43.6x 438x 660mm) | Rack Units | 1 RU |
Connectivity Solutions
800G Spine-Leaf Backend Fabric
200G/400G Spine-Leaf Fabric
Features
Quantum™-2 InfiniBand Switches Deliver the Highest Performance and Port Density
Non-blocking or Bidirectional Bandwidth Ensures Flexible Network
NVIDIA Quantum-2 brings a high-speed interconnect for up to 400Gb/s, extremely low-latency and scalable solution that accelerates research, innovation, and product development for AI developers and scientific researchers.
Hot-swappable Redundant Power and Fans
Hardware-level redundancy protection to ensure business continuity. 80 gold+ and energy star certified powers save money on your power bill, and improves longevity and reliability.
In-Network Computing Enables Higher Performance and Scale
Scalable Hierarchical Aggregation and Reduction Protocol (SHARP)™ technology offloads collective communication operations from the CPU to the switch network, crucial for computing applications.
Self-Healing Ability Enhances System Performance and Utilization
With self-healing networking capabilities, it overcomes link failures and recoveries the network 5,000X faster than any software-based solution, achieving a stable and scalable system.
InfiniBand Proven Adaptive Routing Performance
The adaptive routing algorithms help to prevent packet delivery failures. It also minimises network congestion and increases the network performance.
Multiple Management Methods for Easy Network Maintenance
Supporting SNMP, CLI, WEB, JSON, and the advanced NVIDIA Unified Fabric Manager (UFM®) platform to realize higher utilization and reduce overall opex of the modern data center network.
Why Choose Us
Company Profile
CONTACT US
Take advantage of our unrivaled knowledge and experience, we offer you the best customization service.
SEND US A MESSAGE
HOTLINE
+8613509645699
EMAIL
RECOMMENDED
They are all manufactured according to the strictest international standards. Our products have received favor from both domestic and foreign markets.
They are now widely exporting to 200 countries.
0086 13682472227
