NVIDIA/Mellanox MMS4A50-XM (980-9IAS0-00XM00) Compatible 1.6T 2xFR4 OSFP224 IHS/Closed Finned Top PAM4 Broadcom 3nm DSP (Sian3 | BCM83628) 1310nm 2km SMF DOM Dual LC Duplex InfiniBand XDR Silicon Photonics Transceiver Module for Quantum-X800 Air-Cooled Switches

#102790
Model: OSFP-1.6T-2xFR4H
Sold: 5k+
In Production: 1k | Delivery from Jan. 2026
US$
Brand
NADDOD (InfiniBand)
NADDOD (InfiniBand)
Chip Solutions
Broadcom Sian3 | BCM83628
Broadcom Sian3 | BCM83628

Item Spotlights

  • Built-in Broadcom 3nm DSP (Sian3 BCM83628) and self-developed silicon photonics chip.
  • Fully validated for interoperability with NVIDIA Quantum-X800 air-cooled switches.
  • Maximum power consumption is 26W.
  • 8x200G-PAM4 electrical modulation.
  • Compliant with OSFP MSA, IEEE 802.3dj_D1.1 protocol, and CMIS 5.2.
  • 30-Day Free Return, 1-Year Free Replacement, 3-Year Warranty, Lifetime After-sales Technical Support.
1.6T 2xFR4 OSFP224 MMS4A50-XM 1310nm 2km InfiniBand XDR Transceiver for Mellanox (SMF, IHS/Closed Finned Top)
NVIDIA/Mellanox MMS4A50-XM (980-9IAS0-00XM00) Compatible 1.6T 2xFR4 OSFP224 IHS/Closed Finned Top PAM4 Broadcom 3nm DSP (Sian3 | BCM83628) 1310nm 2km SMF DOM Dual LC Duplex InfiniBand XDR Silicon Photonics Transceiver Module for Quantum-X800 Air-Cooled Switches
Specifications
Applications
Product Highlights
Questions & Answers
Customer Reviews
Resources
Specifications
Applications
Product Highlights
Questions & Answers
Customer Reviews
Resources

Description

NVIDIA/Mellanox MMS4A50-XM (980-9IAS0-00XM00) Compatible 1.6T 2xFR4 InfiniBand XDR Optical Transceiver (Twin-port OSFP224, Broadcom 3nm DSP – Sian3 BCM83628, 1310nm, 2km, OS2, Dual LC Duplex, DOM, SMF, IHS/Closed Finned Top)

NADDOD OSFP-1.6T-2xFR4H is a high-speed, low-latency optical transceiver designed for 1.6Tbps data center interconnects and InfiniBand XDR networks. It supports link distances up to 2km over single-mode fiber (SMF) using a 2xFR4 architecture with two LC duplex ports, each carrying 4x200G PAM4 channels, delivering 800G per port and an aggregate bandwidth of 1.6Tbps.

The transceiver integrates a Broadcom 3nm DSP (Sian3 BCM83628) with NADDOD's self-developed silicon photonics chipset, enabling ultra-low bit error rates (BER), robust signal integrity, and high end-to-end link reliability at 1.6T speeds. Optimized for 1.6T InfiniBand XDR switch-to-switch interconnects, the OSFP-1.6T-2xFR4H is fully validated for interoperability with NVIDIA Quantum-X800 air-cooled switches, making it an ideal optical connectivity solution for supercomputing systems, high-density GPU clusters, and HPC data center environments.

Specifications

Form Factor
OSFP224
Distance
2km
Wavelength
1310nm
Connector
Dual LC Duplex
Power Consumption
≤26W
Transmitter
DFB (SiPh Based)
Receiver
PIN
Media
SMF
Modulation (Electrical)
8x212Gb/s PAM4
Modulation (Optical)
Two ports 4x212Gb/s PAM4
Case Temperature (℃)
0 to 70°C (32 to 158°F)
Protocol
IB XDR, 1.6T Ethernet Compliant

Applications

Product Highlights

3nm DSP × NADDOD SiPh: Built for High-Bandwidth, Long-Reach Interconnect

As XDR network bandwidth continues to increase, long-reach links place higher demands on power efficiency and link stability. NADDOD 1.6T 2xFR4 transceiver features a co-design of Broadcom 3nm DSP (BCM83628) and self-developed silicon photonics chips, delivering lower power consumption, better thermal performance, and more stable links at a 2km distance. Compared with common 5nm DSP solutions, the transceiver reduces power consumption by over 20%, significantly easing thermal pressure on high-density switches, lowering port failure rates, and ensuring long-reach link stability.

LC Connector & Closed Top Housing: Simplify the Deployment of High-Density XDR Cluster

NADDOD 1.6T 2×FR4 transceiver features an LC connector and a Closed Top housing, designed for NVIDIA Quantum‑X800 (Q3400‑RA/Q3200‑RA) switch interconnects. The LC connector keeps interfaces clean, enables quick replacement of same-interface patch cords, thereby improving maintenance efficiency. The Closed Top housing protects the transceiver's fins in data center and campus long‑reach interconnects, optimizes heat dissipation, and suppresses EMI, ensuring excellent signal integrity in high-density deployments.

Why NADDOD

  • Module Availability
    Worry-Free - Rigorous authentic testing!
  • Multi-version Device Compatibility
    Multi-Version - Easy adaptation for each module!
  • High-Performance
    Actual Test Data-Better results intuitively!

Our Approach

Test scene
Test scene
All tests were conducted in a real deployment environment to validate compatibility, connectivity, and long-term stability. NADDOD 1.6T 2xFR4 transceivers maintained stable operation on the NVIDIA Quantum-X800 Q3400-RA switch under full-port, full-load conditions.
Test result
NVIDIA Quantum-X800 Q3400-RA XDR Switch
Software version: 25.02.6007
  • Multi-Version
    Switch Side Testing
    Multi-Version Testing
    Verified across multiple software versions of the Quantum-X800 Q3400-RA switch, NADDOD 1.6T transceivers operate seamlessly, ensuring plug and play in real XDR clusters.
  • Connectivity
    Switch Side Testing
    Connectivity Testing
    During continuous full-load operation, NADDOD 1.6T transceivers keep all switch ports up without link interruptions, providing stable, high-speed connectivity for high-density XDR clusters.
  • BER
    Switch Side Testing
    BER Testing
    Under continuous full-load operation, NADDOD 1.6T transceivers achieve an ultra-low BER, ensuring consistent and reliable data transmission for demanding XDR workloads.
Test result
Test result
Test result
Compare Items
OSFP-1.6T-2xFR4H

OSFP-1.6T-2xFR4H

OSFP-1.6T-2FR4FH

OSFP-1.6T-2FR4FH

OSFP-1.6T-2xDR4H

OSFP-1.6T-2xDR4H

OSFP-1.6T-2DR4FH

OSFP-1.6T-2DR4FH

NVIDIA PN
MMS4A50-XM
/
MMS4A00-XM
MMS4A00-XM-FLT
Form Factor
OSFP224
OSFP224
OSFP224
OSFP224
Thermal Design
IHS/Closed Finned Top
RHS/Flat Top
IHS/Closed Finned Top
RHS/Flat Top
Media
SMF
SMF
SMF
SMF
Center Wavelength
1310nm
1310nm
1310nm
1310nm
Connector
Dual LC Duplex
Dual LC Duplex
Dual MPO-12/APC
Dual MPO-12/APC
Transmission Distance
2km
2km
500m
500m
Electrical Modulation
8x212Gb/s PAM4
8x212Gb/s PAM4
8x212Gb/s PAM4
8x212Gb/s PAM4
Optical Modulation
Two ports 4x212Gb/s PAM4
Two ports 4x212Gb/s PAM4
Two ports 4x212Gb/s PAM4
Two ports 4x212Gb/s PAM4
Power Consumption
≤26W
≤26W
≤25W
≤25W
Transmitter Type
DFB (SiPh Based)
DFB (SiPh Based)
DFB (SiPh Based)
DFB (SiPh Based)
Matching Cables
LC to LC: S2LCUD
LC to LC: S2LCUD
MTP-12 APC Type B OS2: S2MTPA12FB
MTP-12 APC Type B OS2: S2MTPA12FB
Application
1.6T Air-Cooled Switch-to-Switch Interconnect
1.6T Liquid-Cooled Switch-to-Switch Interconnect
1.6T Air-Cooled Switch-to-Switch Interconnect; 1.6T Air-Cooled Switch–to–800G ConnectX-8 HCA Interconnect
1.6T Liquid-Cooled Switch-to-Switch Interconnect

Questions & Answers

Ask a Question
Q:
What are the practical differences of 3nm DSP over common 5nm DSP solutions in real use?
A:
NADDOD's 1.6T transceiver features Broadcom's 3nm DSP (BCM83628). It boasts lower power consumption and better overall performance than 5nm DSP solutions, while significantly lowering the port failure rate and further enhancing link stability in actual deployment. Tested on the NVIDIA Quantum-X800 Q3400 switch, the 3nm solution delivers higher energy efficiency and stability, ensuring efficient and reliable operation of large AI clusters.
Q:
When building or upgrading an AI cluster, what application scenarios and computing scale require this 1.6T XDR transceiver?
A:
The 1.6T XDR transceiver is designed for AI computing scenarios with high network performance requirements, and is suitable for medium to ultra-large scale AI clusters. For medium and large-scale model training and inference scenarios, it meets the requirements of efficient data exchange and computing power expansion. For ultra-large GPU clusters and factory-level AI deployments, it delivers higher bandwidth density, ensuring smooth cluster operation and supporting stable long-term expansion.
Q:
I plan to purchase about 1000 XDR transceivers in one batch for cluster upgrade, what is the current production capacity and expected delivery time?
A:
NADDOD's XDR transceivers are not sample or R&D stage products, and have been deployed in batches in real AI clusters with a stable mass production and delivery system. We have sufficient supply capacity with short delivery time, and can fully support large-scale project-level delivery. For your specific procurement volume and deployment plan, you may directly contact your dedicated account manager or learn about the detailed delivery time via sales@naddod.com.
View More

Customer Reviews

5.0
8 Reviews
  • 5 Star
    100%
  • 4 Star
    0%
  • 3 Star
    0%
  • 2 Star
    0%
  • 1 Star
    0%
All Reviews (8)
  • Verified Purchase
    Verified Purchase
    5.0
    Would definitely reorder for other projects—works great on NVIDIA switches, consistent performance.
    Helpful (10)Comments
  • Verified Purchase
    Verified Purchase
    5.0
    Reliable over long distances. Running these on NVIDIA Quantum-X800 for weeks with no issues.
    Helpful (2)Comments
  • Verified Purchase
    Verified Purchase
    5.0
    Really impressed with the throughput. Dual-port handles high traffic on Quantum-X800 without issues.
    Helpful (2)Comments
  • Verified Purchase
    Verified Purchase
    5.0
    Heat management is solid. Runs cool even under full load on NVIDIA switches.
    Helpful (7)Comments
  • Verified Purchase
    Verified Purchase
    5.0
    Got a batch for our data center—works perfectly on Quantum-X800. Plug-and-play, stable, no headaches.
    Helpful (1)Comments

Quality Certification

ISO140012015
ISO 90012015
ISO450012018
FDA
FCC
CE
RoHS
TUV-Mark
UL
WEEE

What We Supply