Model	Form Factor	CPU Options	Memory Capacity	Storage Bays	GPU Slots
NF5466M6	4U	2× Intel Xeon Gold (up to 28 cores ea.)	Up to 2 TB DDR4	24×3.5″ hot-swap	4× FH PCIe
NF5466M5	4U	2× Intel Xeon Silver/Gold	Up to 1 TB DDR4	24×3.5″ hot-swap	2× FH PCIe
NF5468M6	4U	2× Intel Xeon Silver/Gold	Up to 1 TB DDR4	16×3.5″ + GPU trays	8× FH PCIe
NF8480M6	2U	1× Intel Xeon Gold 5315Y/6330A	Up to 512 GB DDR4	8×2.5″ NVMe	2× FH PCIe
NF8260M5	2U	2× Intel Xeon Gold	Up to 512 GB DDR4	8×2.5″ SAS/SATA	8× FH PCIe
NF5280M6	2U	1× Intel Xeon Silver/Gold	Up to 256 GB DDR4	8×2.5″ SAS/SATA	4× LP PCIe
NF5270M6	2U	2× Intel Xeon Silver	Up to 256 GB DDR4	8×2.5″ or 4×3.5″	–

Category	Model Series	Form Factor	CPU Family	Max GPUs	Drive Bays
X14 Servers	SYS-112C-TN, SYS-112H-TN, SYS-122H-TN, SYS-112B-WR	1U	Intel Xeon Scalable Gen4	–	Up to 4× U.3 or 8×2.5″
	SYS-212H-TN, SYS-222H-TN, SYS-522B-WR	2U	Intel Xeon Scalable Gen4	–	Up to 12× U.3 or 24×2.5″
GPU Servers	AS-4124GO-NART+	4U	Intel Xeon Scalable	4–8	12× U.3 + GPU trays
	AS-4125GS-TNRT2, AS-5126GS-TNRT, AS-5126GS-TNRT2	4U/5U	Intel Xeon Scalable H13/H14	8	16× U.3 + GPU trays
AMD Servers	AS-1115CS-TNR-G1, AS-1115HS-TNR-G1, AS-1125HS-TNR-G1	1U	AMD EPYC™ 7003/7004 Series	–	Up to 8×2.5″
	AS-2015CS-TNR-G1, AS-2015HS-TNR	2U	AMD EPYC™ 7003/7004 Series	–	Up to 12×2.5″

Component	Specification
Model	#BPL-305 Balance 305
Part Number (PN)	BPL-305
WAN Ports	3× 10/100/1000 Mbps GE SFP ports
LAN Ports	3× 10/100/1000 Mbps GE SFP ports
Bypass Ports	2× LAN bypass ports
Throughput	1 Gbps aggregate forwarding
SpeedFusion Peers	2 peers (expandable to 30 with BPL-305-SPF license)
Management	LCD panel, web interface, InControl 2 cloud management
Form Factor	1U rackmount (19″), USB console, optional rack ears
Power	100–240 VAC input, redundant support

Series	Form Factor	Uplinks	Stack/Chassis	Throughput
Catalyst 9300	1U fixed	4× 10G/25G	StackWise-480 (8 members)	480 Gbps
Catalyst 9400	Chassis (5-slot)	10G/25G modules	5-slot, field-replaceable	9 Tbps
Catalyst 9500	1U fixed	4× 40G/100G	N/A	25.6 Tbps
Catalyst 9600	Chassis (3-slot)	40G/100G modules	3-slot, redundant SUPs	25.6 Tbps
Nexus 3000	1U fixed	10/25/40/100G	N/A	2.56 Tbps
Nexus 3550	1U fixed	100G QSFP28	N/A	3.2 Tbps
Nexus 7000	Chassis (8-slot)	10/40G modules	8-slot with redundant SUP	28.8 Tbps
Nexus 9000	1U/2U fixed	25/50/100G	N/A	25.6 Tbps
Business 110	Desktop/1U	Unmanaged 1G	N/A	Up to 128 Gbps
Business 250	1U fixed	10G uplinks	N/A	Up to 176 Gbps
Business 350	1U fixed	10G uplinks	Layer 3 Lite	Up to 280 Gbps

Component	Specification
Model	SA5456M5
CPUs	2× Intel® Xeon® Gold 6152 (22 cores/44 threads, 2.10 GHz/3.70 GHz)
Memory	12×64 GB DDR4 RDIMM @ 2666 MT/s (768 GB total)
Storage	60×16 TB Seagate® Exos® X16 HDDs (960 TB raw)
Networking	1× Intel® XL710-QDA1 40 GbE QSFP+ PCIe 3.0 x8
Chassis	4U rack-mountable; hot-swap 3.5″ drive bays; redundant PSUs and fans
Expansion Slots	8× PCIe 3.0 slots for OCP/GPU/NVMe modules
Management	IPMI with web GUI and Redfish API support

Component	Description	Part Number (PN)
Chassis	ATCA 16-slot chassis with shelf managers and fan modules	C112648
CPU Blade	Dual-socket central processing unit blade	C112772
Storage Module	Storage blade with SAS HDDs	C112773
Power Module	Shelf power module	C112695
Hub Blade	Connectivity blade for ATCA system	C112671
Rear Transition Module	RTM for hub blade	C112670
Carrier Blade	AMC carrier blade	C111975
DSP Blade	Digital signal processor blade	C112635

NVIDIA CONNECTX-7 MCX755106AC-GEAT Dual-Port 200GBE / NDR200 Infiniband Adapter...

Ocena: 4

NVIDIA CONNECTX-7 MCX755106AC-GEAT Dual-Port 200GBE / NDR200 Infiniband Adapter

Kategorie produktów:Komponenty
Numer katalogowy:MCX755106AC-HEAT
Dostępność:In Stock
Stan:Nowy
Cechy produktu:Gotowy do wysyłki
Minimalne zamówienie:1 szt.
Cena katalogowa wynosiła:$1,999.00
Twoja cena: $1,650.00 Oszczędzasz $349.00
Czat teraz Wyślij e-mail

Oddychaj spokojnie. Przyjmujemy zwroty.

Wysyłka: Międzynarodowa wysyłka produktów może wiązać się z procedurami celnymi oraz dodatkowymi opłatami. Zobacz szczegóły

Dostawa: Proszę o dodatkowy czas, jeśli międzynarodowa dostawa podlega procedurze celnej. Zobacz szczegóły

Zwroty: 14 dni na zwroty. Sprzedawca pokrywa koszt zwrotu. Zobacz szczegóły

Darmowa wysyłka. Akceptujemy zamówienia zakupu NET 30 dni. Otrzymaj decyzję w kilka sekund, bez wpływu na Twoją zdolność kredytową.

Jeśli potrzebujesz dużej ilości produktów MCX755106AC-HEAT - zadzwoń do nas na bezpłatny numer WhatsApp: (+86) 151-0113-5020 lub poproś o ofertę na czacie na żywo, a nasz menedżer sprzedaży skontaktuje się z Tobą wkrótce.

Title

NVIDIA ConnectX-7 MCX755106AC-HEAT Dual-Port 200GbE / NDR200 InfiniBand Network Adapter

Keywords

NVIDIA ConnectX-7, MCX755106AC-HEAT, 200Gb Ethernet, NDR200 InfiniBand, dual-port QSFP112, PCIe5 x16 NIC, RoCE/RDMA networking, data center NIC

Description

The MCX755106AC-HEAT is a high-performance network interface card from NVIDIA’s ConnectX-7 family, combining both 200Gb Ethernet and NDR200 InfiniBand capabilities in one dual-port QSFP112 adapter. It’s designed for data center, HPC, AI, cloud infrastructure, and high-throughput RDMA / RoCE traffic patterns.

This adapter fits a PCIe5 x16 interface, enabling very high bandwidth between host server and network fabric, especially under heavy loads. It supports Secure Boot and Crypto Enabled features, making it more suitable for environments where network security and tamper-resistance matter.

Form factor is half-height, half-length (HHHL), dimensions ~68.90 mm × 167.65 mm, meaning it fits a wide range of server chassis. It also has an auxiliary PCIe passive card option plus Cabline SA-II Plus harnesses, which expand compatibility for socket-direct or other deployment-specific cabling topologies.

Operating temperature range is 0-55 °C, with storage set from -40 to 70 °C, which is typical for enterprise NICs. Power draw is about 25.9 W (for the "AC" variant; "AS" variant slightly lower) when used with passive cables under PCIe Gen5 x16 mode.

Because it supports both Ethernet and InfiniBand modes, this NIC is flexible. You can use it for standard TCP/IP 200GbE networking or for high-performance RDMA over InfiniBand (NDR200), depending on network infrastructure. This duality is very useful in mixed-environment data centers.

Key Features

Dual ports of QSFP112 supporting both 200GbE and NDR200 InfiniBand modes.
High-speed PCIe Gen5 x16 host interface for maximum throughput, backward compatible with PCIe4/3.
Secure Boot & Crypto Enabled (AC variant) for enhanced security in networking.
RoCE/RDMA support for low latency, high throughput in data center / HPC workloads.
Auxiliary PCIe extension option via passive card + Cabline SA-II Plus harnesses allows socket-direct style deployment.
Compact HHHL form factor with heatsink (HEAT version), suitable for most standard server racks.
Low power (~25.9W typical under load) for its class, reducing thermal and power overhead per port).

Configuration

Component	Specification / Detail
Part Number / Model	MCX755106AC-HEAT (NVIDIA ConnectX-7)
Ports	2 × QSFP112 (dual-port)
Network Types	Ethernet (200/100/50/25/10GbE), InfiniBand (NDR200/HDR/HDR100 etc.)
Host Interface	PCIe5 x16 (also backward support for PCIe4/3 via SERDES 16/32 GT/s)
Power Consumption	~25.9W (AC variant) ≈24.9W for AS variant under passive cable / typical load
Physical Size	Half-Height Half-Length, ~68.90 mm × 167.65 mm
Operating Temp	0-55 °C (operational) / -40-70 °C (storage)
Special Features	Secure Boot, Crypto Enabled, Socket-Direct passive cable option
Compatibility Modes	RoCE, RDMA, Ethernet, InfiniBand

Compatibility

The MCX755106AC-HEAT works with any server motherboard with a free PCIe x16 slot, preferably supporting PCIe5 to achieve full speed. Servers with PCIe4 will run lower speeds but are compatible. Ensure sufficient cooling and proper bracket height (tall / HHHL) to fit heatsink.

For network connectivity, you must have compatible QSFP112 ports on your network switches or use optical / DAC/CR4/QSFP112 optical transceivers that match the cable type. For InfiniBand mode, your switch must support NDR200 or HDR etc. For Ethernet mode, switches must support 200GbE or lower fallback speeds.

Drivers and firmware should be current: NVIDIA’s ConnectX-7 driver stack (for your OS — Linux, Windows, etc.) plus firmware that supports Secure Boot / Crypto features. Missing updates may limit performance or features (e.g. passive adapter harness option).

Power budget: because the NIC consumes ~25-26W under typical loads with passive cables, ensure the server PSU and airflow can handle this plus any adjacent NICs and cards. Heatsink (HEAT) version will generate some thermal load; airflow at appropriate speeds is necessary.

Usage Scenarios

1) High-Performance Compute / AI Cluster Fabrics: Great for interconnect in GPU/CPU clusters needing very high bandwidth and low latency, especially where RDMA or InfiniBand fabrics are used (NDR200) to avoid network bottlenecks.

2) Data Center Ethernet Backbone: Use it for 200GbE switches/routers interconnect, server uplinks, or leaf/spine architecture where high throughput is required.

3) RoCE / RDMA for Storage Systems: For NVMe-over-Fabric, or distributed storage systems like Ceph or Lustre, or other systems using RDMA, this NIC accelerates storage access by reducing latency and CPU overhead.

4) AI/ML / HPC Inference & Training: Use in inference serving nodes or training nodes where large model weights are shared, reducing data movement overhead across nodes). Also helpful in virtualization of GPU workloads.

5) Secure / Compliance Environments: Because Secure Boot and Crypto Enabled are supported, this card is appropriate where network encryption, trusted boot, and compliance (e.g. for financial, government, or healthcare systems) rank high in requirement.

Frequently Asked Questions

Q: Does MCX755106AC-HEAT require PCIe Gen5 to get full 200Gbps performance, or will it work with Gen4 as well?
A: It will work with PCIe Gen4 and even Gen3 (depending on host), but to reach full advertised throughput (especially for both ports and maximum lane count), PCIe5 x16 is preferred. Gen4 will likely impose some bandwidth ceiling.
Q: Can this adapter operate in both Ethernet 200GbE mode and InfiniBand NDR200 mode interchangeably?
A: Yes — the MCX755106AC-HEAT supports both Ethernet and InfiniBand (NDR200) modes. Mode selection depends on switch/fabric configuration and firmware. It is dual-mode and highly flexible.
Q: What cabling or transceivers are needed to make full use of its QSFP112 ports?
A: You’ll need optical or copper QSFP112/CR4/CR8 cables/transceivers rated for 200Gb/s or fallback levels (100/50/25/10Gb/s). Passive cables may limit reach; check cable spec. Also if using passive cabling, be sure the port and NIC both support that mode.
Q: What are the thermal and mechanical requirements for the HEAT version?
A: HEAT version includes heatsink, so it needs good airflow within the server enclosure. Confirm that the server’s PCIe slot bracket height accommodates tall bracket / heatsink. Also verify power budget—~25.9W under load plus any auxiliary cabling/harness.