RFQ
01Part-number led inquiry path
MQM8700-HS2R can be used as the direct starting point for quotation, BOM sharing and availability discussion.
High-performance 200G InfiniBand switch with 40 QSFP56 ports, 16Tb/s throughput, and SHARP in-network computing for AI/HPC clusters.
RFQ
Inquiry ready
Clear path for part number, quantity and BOM-led contact.
EN / AR
Bilingual buyer flow
Useful for procurement teams coordinating technical review across regions.
Datasheet available
The product datasheet can be downloaded directly from this page.

Selected specs
Ordering code
MQM8700-HS2R(920-9B110-00RH-0M0)
Deployment fit
AI & Machine Learning Clusters – Large‑scale GPU‑based systems (NVIDIA DGX, HGX) requiring 200G interconnect with SHARP for NCCL acceleration.
Follow-up path
Quote / Compatibility / Availability
Prepared for part-number led and BOM-led requests

Product media
When product photography is available it appears here for faster review, and a clean technical outline remains useful for early evaluation when imagery is limited.
Overview
The NVIDIA Quantum QM8700 series (including MQM8700‑HS2R) represents a new class of 200G InfiniBand smart switches, engineered to eliminate bottlenecks in AI, high‑performance computing, and cloud storage environments. With up to forty 200Gb/s ports in a compact 1U form factor, the switch delivers 16 Tb/s aggregate throughput with cut‑through latency below 130 nanoseconds. Built on NVIDIA’s scalable InfiniBand architecture, the MQM8700‑HS2R features an embedded x86 dual‑core processor, integrated Subnet Manager (up to 2,000 nodes), and support for NVIDIA SHARP technology, accelerating collective operations by offloading communication from servers to the network fabric. Designed for extreme flexibility, each 200Gb/s QSFP56 port can be split into two independent 100Gb/s ports, doubling the radix for dense top‑of‑rack deployments. The MQM8700‑HS2R variant (C2P airflow) is a fully managed switch running MLNX‑OS, ideal for enterprises seeking high‑performance networking with simple out‑of‑the‑box management, CLI, WebUI, SNMP, and JSON APIs.
Buying flow
This section gives buyers a practical handoff from technical review into quotation or compatibility follow-up.
Start from MQM8700-HS2R or the product name to reduce ambiguity before quotation starts.
Share quantity, destination or BOM context so the commercial follow-up is aligned with the project scope.
Use the page as the handoff point for stock discussion, compatibility checks and delivery planning.
Trust signals
The page is designed to reduce the distance between specification review and a real commercial inquiry.
RFQ
01MQM8700-HS2R can be used as the direct starting point for quotation, BOM sharing and availability discussion.
Review
02The NVIDIA Quantum MQM8700-HS2R 200G InfiniBand Switch | 40-Port 16Tb/s Managed Switch with C2P Airflow page is positioned to support compatibility questions and project-fit review before commercial action is finalized.
Project
03This model can be framed against use cases such as AI & Machine Learning Clusters – Large‑scale GPU‑based systems (NVIDIA DGX, HGX) requiring 200G interconnect with SHARP for NCCL acceleration. together with quantity and rollout timing.
Language
04The bilingual route supports regional buying teams that need technical review and RFQ handling in two languages.
FAQ
Short answers that give buyers clearer expectations before they move into the quote form.
Yes. This page is designed to move MQM8700-HS2R review directly into quotation, availability or BOM discussion.
Yes. The page can be used to frame compatibility questions around AI & Machine Learning Clusters – Large‑scale GPU‑based systems (NVIDIA DGX, HGX) requiring 200G interconnect with SHARP for NCCL acceleration. before commercial follow-up.
Yes. Related products within the same category give buyers an internal comparison path before they submit an inquiry.
Yes. The inquiry path is designed to accept part numbers, quantity, BOM context and availability requirements in one submission.
Related products
Internal links that support model comparison and adjacent product discovery.
High-performance 100G InfiniBand switch with 36 QSFP28 ports, 7.2Tb/s throughput, SHARP acceleration, and P2C airflow for HPC/AI data centers.

High-performance 36-port 100G InfiniBand switch with 7.2Tb/s throughput, ultra-low latency, and UFM-ready for HPC/AI data centers. Features SHARP acceleration.

High-performance 200G InfiniBand switch with 40 QSFP56 ports, 16Tb/s throughput, and SHARP acceleration for AI/HPC clusters. Low latency, managed, RoHS compliant.

High-performance 40-port 200G InfiniBand switch with 16Tb/s throughput, UFM ready for AI clusters and HPC. Features SHARP acceleration, dual PSU, and sub-130ns latency.

High-performance 200G InfiniBand switch with 40 QSFP56 ports, 16Tb/s throughput, and UFM-ready for AI clusters & HPC data centers.

64-port 400Gb/s NDR InfiniBand switch with 51.2Tb/s throughput, SHARPv3 AI acceleration, and C2P airflow. Ideal for HPC and AI workloads.

High-performance 64-port 400G InfiniBand switch with 51.2 Tb/s throughput, SHARPv3 acceleration, and P2C airflow for AI/HPC clusters.

64-port 400G InfiniBand managed switch with 51.2 Tb/s throughput, SHARPv3 acceleration, and ultra-low latency for AI/HPC clusters.

High-performance 400Gb/s InfiniBand switch with 64 ports, 51.2Tb/s throughput, and SHARPv3 acceleration for AI/HPC data centers. 1U rack-mount design.

MQM8700-HS2R
Quick quote