Qm8700-HS2r 40 Port Hdr 200g Ib Switch Supports Dragonfly+ Topology.

• Customization: Available
• Communication Mode: Full Duplex
• Type: Network Switch
• Model NO.: MQM8700-HS2R
• Transmission Rate: 200GB/S
• Ports: 40
• Aggregate Bandwidth: 1.6tbps
• Forwarding Rate: 7.2 Billion Packets Per Second (Bpps)
• Port-to-Port Latency: < 130ns
• Cooling Design: Hot-Swappable Fan, N+1 Redundancy
• Transport Package: Carton
• Specification: Original specification
• Trademark: NVIDIA
• Origin: China

Product Description

Product Description

Scaling Out High-Performance Computing (HPC), AI, Cloud Applications, and Storage Infrastructures with 200G InfiniBand Fixed-Configuration Switches

Faster servers combined with high-performance storage and applications that use increasingly complex computations are causing data bandwidth requirements to spiral upward. As servers are deployed with next-generation processors, HPC, AI, and hyperscale cloud environments will need every last bit of network bandwidth. 
NVIDIA Quantum QM8700 and QM8790 200 gigabits per second (Gb/s) InfiniBand fixed-configuration switches provide up to forty 200Gb/s ports with 16 terabits per second (Tb/s) of non-blocking bandwidth or eighty 100Gb/s ports with full bidirectional bandwidth per port with extremely low latency-an ideal choice for building flexible and scalable data centers at any size.

Collective Communication Acceleration
The QM8700/QM8790 switches integrate NVIDIA's hierarchical aggregation protocol to accelerate HPC and deep learning frameworks (e.g., MPI, NCCL) via built-in hardware, reducing redundant server data transfers and enabling linear aggregation of large data vectors for performance gains.
Network Design & Topology Optimization
High-Density 100Gb/s:With ConnectX-6 adapters, the QM8700 supports 80×100Gb/s ports (200Gb/s ports split into dual 100Gb/s lanes), ideal for high-density rack ToR scenarios.
Flexible Topology Support:Compatible with Fat Tree, DragonFly+, etc., with backward compatibility and rich software ecosystem.

Enhanced Management
QM8700 (Internal Management)
On-board subnet manager enables plug-and-play for 2,000 nodes. Managed via CLI/WebUI/SNMP/JSON with MLNX-OS®.
QM8790 (External Management)
Leverages NVIDIA UFM® for centralized provisioning, monitoring, and maintenance to boost efficiency and reduce OPEX.
Efficient Cluster Building
QM8700/QM8790 Switches:

Cost-effective for HPC clusters with static/adaptive routing, congestion control, and QoS for modern topologies.
Eliminate bottlenecks to maximize bandwidth.
Low-power design with dynamic power savings for partial ports, optimizing TCO and ROI through scalability and energy efficiency.

Basic information	Brand	NVIDIA
	Model	MQM8700-HS2R
	Series	Quantum series HDR switch
Hardware parameters	Port Configuration	40 × 200Gb/s HDR QSFP56 port (which can be split into 80 × 100Gb/s HDR100 port)
	Interface Type	QSFP56
	Power Redundancy	Dual redundant hot plug power supply (AC 100-127V/200-240V)
	Cooling Design	Hot-swappable fan, N+1 redundancy
	Physical Dimensions	1U height, 43.6mm × 433.2mm × 590.6mm(H × W × D).
	CPU	x86 ComEx Broadwell D-1508
	Memory	8GB DDR4
	Management Ports	RJ45 Ethernet port, RS232 console port and USB management port.
Performance characteristics	Aggregate Bandwidth	16Tb/s Non-blocking bandwidth
	Forwarding Rate	7.2 billion packets per second (Bpps)
	Port-to-Port Latency	< 130ns
	Network Acceleration	Adaptive routing, congestion control
	Protocol Compatibility	InfiniBand 1.3 standard, compatible with HDR/EDR/FDR/QDR rate.
Application scenario	Use Cases	HPC High Performance Computing, AI/ML Training and Reasoning, Enterprise Storage Network, Very Large Data Center.
	Deployment Topology	ToR leaf switch, supporting DragonFly+, SlimFly and other topologies.
Reliability and environment	Redundancy Design	Power supply 1+1 redundancy, fan N+1 redundancy
	Operating Temperature	0ºC to 40ºC

	Storage Temperature	-40ºC to 70ºC
	Humidity Range	10%-85% (operational), 10%-90% (non-operational)
	Warranty	1-year standard warranty (extendable to 3 years)
additional function	Management OS	MLNX-OS (based on Linux)
	Split Cable Support	Supports splitting ports through branch cables (for example, 200G→2×100G).
	Virtualization Support	Support VL2VL mapping (virtual channel to virtual channel routing)
ORDERABLE PART NUMBER (OPN)	MQM8700-HS2R	NVIDIA Quantum 200Gb/s InfiniBand switch, 40 QSFP56 ports, two power supplies (AC), x86 dual core, standard depth, C2P airflow,rail kit

For Brocade FC SAN Fiber Optic Switch	For NVIDIA Ethernet Switch	For NVIDIA InfiniBand Switch
For Brocade G610	For NVIDIA SN5000 Series	For NVIDIA Quantum-X800 Series
For Brocade G620	For NVIDIA SN4000 Series	For NVIDIA Quantum-2 QM9700 Series
For Brocade G630	For NVIDIA SN3000 Series	For NVIDIA QUANTUM QM8700 Series
For Brocade G710	For NVIDIA SN2000 Series
For Brocade G720
For Brocade G730
For Brocade X6 Directors
For Brocade X7 Directors

About Us

A national high-tech company featuring R&D, designing, production,marketing and service, Beijing HengzhengTc Sci-Tech co. Ltd. providesprofessional solutions for high-speed Internet access products and smarttelecommunications products. lt's products include PCle and Ocp servernetwork adapter, optical module, DAC/AOC/ACC/AEC and MTP/MPT opti-cal fiber patch cord, and can be produced on demand.

Its1G/10G/25G/40G/50G/100G/200G/400G/800G Ethernet product seriesand EDR, HDR, NDR and XDR InfiniBand product series can be used inequipment of all mainstream brands, and can be applied in cloud servic-es, high-caliber computing, enterprises, telecommunications, storage, Aland data centers. Beijing HengzhengTc Sci-Tech Co. Ltd. provides a36-month warranty for all its products.

We also provide parts of world-famous brand Al servers, including GPU,DPU, RAlD controller, network adapter, ssD, among others. Guided byour clients'demands, we also provide solutions for Brocade FC SAN,Nvidia InfiniBand and high-speed Ethernet.

 With 16 years of experience in the industry and five years of export histo-ry, we value the client-centered principle and sincerely serve every do-mestic and international client.

1. Why choose us?
Our team has over 10 years of experience in AI server accessories and high-speed network solutions (FC SAN/InfiniBand/Ethernet), with deep industry expertise to deliver optimized solutions for various scenarios. 
We maintain a stable supply chain with long-term partnerships with top manufacturers, ensuring sufficient stock and reliable lead times. We provide one-stop services including product selection, solution design and 24/7 after-sales support. 
Benefiting from bulk purchasing, we offer highly cost-effective 100% original products at competitive prices.
 
2. Is the product brand new?
All products are 100% original and new. Official warranty is provided for authorized brands, and self-developed products pass strict quality inspection. Official verification is supported.
 
3. How long after payment will the goods be dispatched?
In-stock orders: Ship within 1–3 working days after payment confirmation; urgent orders are prioritized.
Out-of-stock/custom orders: Lead time depends on inventory or production, confirmed by customer service. 
Delivery may be delayed during holidays. Please check with us before ordering.
 
4. Is customization acceptable? What is the MOQ?
Customization available for self-developed network cards, optical modules and high-speed cables.
MOQ: 50 pieces for basic customization; ≥200 pieces for complex specifications.
Authorized products only support original standard models, no customization. 
Contact customer service for details.
 
5. Which payment methods and currencies are accepted?
We accept bank transfers (online or counter) to our corporate account. 
Order number must be noted for payment verification. 
Both RMB and USD are supported.