The NVIDIA Quantum-2-based QM9700 and QM9790 switch systems deliver 64 ports of 400Gb/s InfiniBand per port, packed into a 1U standard chassis. Each switch carries an impressive 51.2 terabits per second (Tb/s) of aggregated bidirectional
throughput and a landmark capacity exceeding 66.5 billion packets per second (BPPS). Supporting NVIDIA's advanced 400Gb/s interconnect technology, NVIDIA Quantum-2 is a high-speed, extremely low-latency, and scalable networking solution. Key features incorporated include state-of-the-art technologies such as remote direct-memory access (RDMA), adaptive routing, and NVIDIA® Scalable Hierarchical Aggregation and Reduction Protocol.
Basic information |
Model |
MQM9790-NS2R |
|
Brand |
NVIDIA® Mellanox® |
|
Device Type |
Intelligent InfiniBand switch (AI/HPC optimization) |
performance parameter |
Data Rate |
400G NDR/200G HDR/100G EDR/56G FDR/40G ODR |
|
Packet Forwarding Rate |
51.2 TB/s (full duplex) |
|
Port Density |
64 port (OSFP interface) |
Hardware specification |
CPU |
X86 architecture Intel® Coffee Lake i3 processor |
|
Memory |
8GB DDR4 (single channel) |
|
Operating System |
MLNX-OS(based on Linux kernel) |
Heat dissipation design |
Airflow Direction |
Connector-to-Port, C2P |
|
Cooling Compatibility |
Closed machine room architecture adapted to cold channel |
Protocol and compatibility |
Supported Protocols |
InfiniBand NDR/HDR/EDR, RoCEv2, TCP/IP |
|
Acceleration Engine |
SHARPv3(Extensible Layered Aggregation and Reduction Protocol) |
|
Topology Support |
Fat Tree, Dragonfly+, Hypercube |
physical characteristics |
Rack Unit |
1U standard rack design |
|
Power Supply |
Dual redundant power supply (2000W AC) |
Application scenario |
Typical Use Cases |
AI training cluster, supercomputing center interconnection, quantum computing network, core exchange of enterprise data center. |
Ordering information |
MQM9790-NS2R |
64 NDR ports, 32 OSFP ports, unmanaged, C2P airflow (reverse) |
Top performance
Ultra-high bandwidth and low latency: It supports NDR 400 G (single port 400Gb/s, total bandwidth 51.2Tb/s), and the latency is less than 100ns, which is specially optimized for high throughput scenarios such as AI training and HPC.
Intelligent acceleration: integrating v3 network computing, greatly reducing GPU communication load and improving AI training efficiency; Support adaptive routing and QoS isolation to dynamically optimize network traffic.
Reliability and compatibility
Industrial-grade design: wide temperature power supply (-20 C to 70°C) and anti-vibration port, suitable for harsh environments such as edge computing and vehicle data center; The NS2F cooling architecture is compatible with standard computer rooms, and the power consumption is as low as 1.2kW.
Multi-protocol compatibility: downward support EDR/HDR/FDR, seamless access to existing GPU clusters; It can be upgraded to 800G OSFP optical module in the future.
Flexible management
Plug and Play: Built-in subnet manager supports rapid deployment of 2000 nodes; Provide CLI/Web interface and automatic operation and maintenance tools (MLNX-OS).
Wide scene coverage
It is suitable for AI training clusters, supercomputing centers, edge computing and multi-tenant cloud resource pools, and meets the needs of all scenarios from data centers to industrial edges.
After Sales Service
Q:Are you trading company or manufacturer?
A:We are factory.
Q:How long is your delivery time?
A:Generally it is 2-5 days if the goods are in stock. or it is 10 days if the goods are not in stock, it is according to quantity.
Q:Do you have MOQ?
A:For stock products,we don't have MOQ. For custom product,we ask for low MOQ.
Q:Can you offer a better price?Any discount?
A:Yes,surely. We're source factory and providing reasonable price.
Q:What is your warranty period?
A:Different products have different warranties.This warranty does not cover damage caused by man-made damage,improper care,negligence,normal wear tear,and force majeure such as natural disasters,earthquakes,fires ,etc.