RFQ
01Part-number led inquiry path
900-9X81Q-00CN-ST0 can be used as the direct starting point for quotation, BOM sharing and availability discussion.
Network adapters & DPUs• 900-9X81Q-00CN-ST0
NVIDIA ConnectX-8 SuperNIC C8240 | 800G AI Networking Adapter for Hyperscale GPU Clusters
800Gb/s dual-port AI networking adapter with PCIe Gen6, InfiniBand/Ethernet support, and GPUDirect RDMA for hyperscale GPU 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.
Fast technical snapshotDatasheet available
900-9X81Q-00CN-ST0
Product photoCMS image ready
Selected specs
Deployment fit
The ConnectX-8 SuperNIC C8240 is purpose-built for next-generation AI fabrics and hyperscale cloud environments:
Follow-up path
Quote / Compatibility / Availability
Prepared for part-number led and BOM-led requests
900-9X81Q-00CN-ST0
Product photoCMS image ready
Product media
From product visual to RFQ context
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.
01Product imagery when available
02Clear technical outline for fast review
03Built for specification review before inquiry
Overview
Product overview
The NVIDIA ConnectX-8 SuperNIC (C8240, 900-9X81Q-00CN-ST0) represents a generational leap in AI fabric acceleration. Supporting up to 800 gigabits per second (Gb/s) over InfiniBand or Ethernet, this adapter eliminates network bottlenecks in large-scale GPU clusters. With native PCIe Gen6 (up to 48 lanes) and advanced features such as NVIDIA GPUDirect RDMA, SHARP in-network computing, and programmable congestion control, the ConnectX-8 ensures maximum throughput and lowest latency for training, inference, and data-intensive HPC workloads. Its power-efficient design aligns with sustainable AI data center goals while enabling scaling beyond hundreds of thousands of GPUs. 800Gb/s total bandwidth – supports 800/400/200/100 Gb/s InfiniBand speeds and 400/200/100/50/25 Gb/s Ethernet. PCIe Gen6 host interface – up to 48 lanes, low overhead, and Multi-Host support for up to four hosts.
Key features
Typical applications
- The ConnectX-8 SuperNIC C8240 is purpose-built for next-generation AI fabrics and hyperscale cloud environments:
- AI Factories & Large Language Model Clusters – trillion-parameter model training with 800G front-end and back-end networks.
- High-Performance Computing (HPC) – SHARPv3 in-network reduction accelerates MPI collectives for scientific simulations.
- GPU-Accelerated Cloud Data Centers – multi-tenant isolation, overlay offloads, and advanced QoS.
- Enterprise AI Infrastructure – from inference farms to AI data platforms requiring deterministic low latency.
- Storage & Converged Fabrics – GPUDirect Storage and RoCEv2 for NVMe-oF and distributed file systems.
Buying flow
How this product review turns into a real inquiry
This section gives buyers a practical handoff from technical review into quotation or compatibility follow-up.
01
Identify the exact target model
Start from 900-9X81Q-00CN-ST0 or the product name to reduce ambiguity before quotation starts.
02
Add quantity or deployment context
Share quantity, destination or BOM context so the commercial follow-up is aligned with the project scope.
03
Move into availability and fit review
Use the page as the handoff point for stock discussion, compatibility checks and delivery planning.
Technical snapshot
Trust signals
Why buyers use this page to review 900-9X81Q-00CN-ST0
The page is designed to reduce the distance between specification review and a real commercial inquiry.
Review
02Compatibility review before follow-up
The NVIDIA ConnectX-8 SuperNIC C8240 | 800G AI Networking Adapter for Hyperscale GPU Clusters page is positioned to support compatibility questions and project-fit review before commercial action is finalized.
Project
03Project and quantity alignment
This model can be framed against use cases such as The ConnectX-8 SuperNIC C8240 is purpose-built for next-generation AI fabrics and hyperscale cloud environments: together with quantity and rollout timing.
Language
04English and Arabic follow-up
The bilingual route supports regional buying teams that need technical review and RFQ handling in two languages.
FAQ
Frequently asked questions about 900-9X81Q-00CN-ST0
Short answers that give buyers clearer expectations before they move into the quote form.
Can I request a quote for 900-9X81Q-00CN-ST0 directly from this page?01
Yes. This page is designed to move 900-9X81Q-00CN-ST0 review directly into quotation, availability or BOM discussion.
Does 900-9X81Q-00CN-ST0 support compatibility discussion before purchase?02
Yes. The page can be used to frame compatibility questions around The ConnectX-8 SuperNIC C8240 is purpose-built for next-generation AI fabrics and hyperscale cloud environments: before commercial follow-up.
Can 900-9X81Q-00CN-ST0 be compared with nearby models in the same family?03
Yes. Related products within the same category give buyers an internal comparison path before they submit an inquiry.
Can I send quantity or a BOM list with the inquiry?04
Yes. The inquiry path is designed to accept part numbers, quantity, BOM context and availability requirements in one submission.
Related products
Related products in the same family
Internal links that support model comparison and adjacent product discovery.
MCX516A-CCAT• Network adapters & DPUs
MCX516A-CCAT Dual-Port 100GbE Ethernet Adapter by NVIDIA
Dual-port 100GbE PCIe adapter with RoCE, 750ns latency, 200Mpps throughput. Ideal for AI, cloud, and storage with NVMe-oF, SR-IOV, and ASAP2 offloads.
MCX516A-CCAT
Product photoCMS image ready
- Low-profile PCIe add-in card. Ships with tall bracket mounted, short bracket included.
- PCIe 3.0 x16 (compatible with x8, x4, x2, x1; auto-negotiated)
- Up to 200 million messages per second (Mpps); 197 Mpps with DPDK
- SR-IOV: up to 512 Virtual Functions, 8 Physical Functions per port
MCX4121A-XCAT• Network adapters & DPUs
NVIDIA ConnectX-4 Lx EN MCX4121A-XCAT – Dual-Port 10GbE SFP28 Adapter Card with RoCE Virtualization Offloads
Dual-port 10GbE SFP28 adapter with RoCE, SR-IOV virtualization, and VXLAN offloads. Ideal for cloud, storage, and database servers requiring low latency.
MCX4121A-XCAT
Product photoCMS image ready
- PCIe 3.0 x8 (compatible with x16, x4, x2, x1; auto-negotiated)
- SR-IOV: up to 256 Virtual Functions, 8 Physical Functions per port
- Yes – RDMA over Converged Ethernet (RoCE)
- TCP/UDP checksum offload, LSO/LRO, RSS, TSS, VLAN insertion/stripping
MCX631102AN-ADAT• Network adapters & DPUs
NVIDIA ConnectX-6 Lx MCX631102AS-ADAT OCP 3.0 Adapter for Cloud & Enterprise
High-performance OCP 3.0 SmartNIC with 25/50GbE ports, PCIe Gen4, IPsec encryption, and SDN acceleration for cloud data centers.
MCX631102AN-ADAT
Product photoCMS image ready
- OCP 3.0 Small Form Factor (SFF), hot-pluggable
- PCIe Gen4 x8 (compatible with PCIe Gen3 x8)
- Zero-Touch RoCE, RoCE Congestion Control, IPsec over RoCE
- Inline IPsec (AES-XTS 256/512-bit), hardware root-of-trust, secure firmware update
MCX631432AN-ADAB• Network adapters & DPUs
NVIDIA ConnectX-6 Lx MCX631432AN-ADAB 25/50GbE SmartNIC
Dual-port 25/50GbE SmartNIC with PCIe Gen4, IPsec encryption, and Zero-Touch RoCE. Ideal for cloud, enterprise, and NFV workloads with 75Mpps throughput.
MCX631432AN-ADAB
Product photoCMS image ready
- PCIe Low Profile (also available in OCP 3.0 SFF)
- 2x 10/25GbE or 1x 50GbE (SFP28 / QSFP28 depending on SKU variant)
- PCIe Gen4 x8 (compatible with PCIe Gen3 x8)
- Zero-Touch RoCE, RoCE Congestion Control, IPsec over RoCE
MCX653106A-HDAT-SP• Network adapters & DPUs
NVIDIA ConnectX-6 MCX653106A-HDAT 200Gb/s Dual-Port InfiniBand Smart Adapter
Dual-port 200Gb/s InfiniBand smart adapter with PCIe 4.0 support, hardware encryption, and in-network computing for HPC and AI workloads.
MCX653106A-HDAT-SP
Product photoCMS image ready
- PCIe Gen 4.0/3.0 x16 (also supports x8, x4, x2, x1)
- RDMA, XRC, DCT, ODP, Hardware Congestion Control, 16M I/O channels, 8 VLs + VL15
- RoCE, LSO/LRO, checksum offload, RSS/TSS, VXLAN/NVGRE/Geneve offload
- NVMe-oF (target/initiator), T10-DIF, SRP, iSER, SMB Direct
MCX75310AAS-NEAT• Network adapters & DPUs
NVIDIA ConnectX-7 MCX75310AAS-NEAT Dual-Port 400Gb/s InfiniBand & Ethernet Smart Adapter – PCIe 5.0 x16, NDR
High-performance 400Gb/s dual-port adapter with PCIe 5.0 x16, hardware security offloads, and NVMe-oF support for AI/HPC data centers.
MCX75310AAS-NEAT
Product photoCMS image ready
- Ordering code
- MCX75310AAS-NEAT(900-9X766-003N-SQ0)
- PCIe 5.0 x16 (32 lanes)
- IPsec, TLS 1.3, MACsec, AES-XTS
MCX755106AS-HEAT• Network adapters & DPUs
NVIDIA ConnectX-7 MCX755106AS-HEAT NDR 400Gb/s InfiniBand Smart Adapter
Dual-port 400Gb/s InfiniBand & RoCE smart adapter with PCIe Gen5 x16, GPUDirect RDMA, and hardware security offloads for AI, HPC, and cloud data centers.
MCX755106AS-HEAT
Product photoCMS image ready
- Ordering code
- MCX755106AS-HEAT(900-9X7AH-0078-DTZ)
- PCIe HHHL (Half Height Half Length), FHHL bracket optional
- PCIe Gen5.0 x16 (up to 32 lanes, supporting bifurcation & Multi-Host)
C8180• Network adapters & DPUs
NVIDIA ConnectX-8 SuperNIC C8180（900-9X81E-00EX-ST0) 800G AI Networking Adapter
800Gb/s AI networking adapter with PCIe Gen6, InfiniBand/Ethernet support, and GPUDirect RDMA for hyperscale AI data centers.
C8180
Product photoCMS image ready
- Ordering code
- C8180(900-9X81E-00EX-ST0)
MCX555A-ECAT• Network adapters & DPUs
NVIDIA MCX555A-ECAT 100Gb/s Single-Port QSFP28 InfiniBand Adapter PCIe 3.0 x16 ConnectX-5 Network Card
High-performance 100Gb/s InfiniBand adapter with PCIe 3.0 x16, QSFP28 port, RDMA, and NVMe-oF offloads for HPC and AI workloads.
MCX555A-ECAT
Product photoCMS image ready
- 1x QSFP28, up to 100Gb/s InfiniBand (EDR) and 100GbE
- PCI Express 3.0 x16 (compatible with x8, x4, x2, x1)
- 100GbE, 50GbE, 40GbE, 25GbE, 10GbE, 1GbE; IEEE 802.3cd, 802.3bj, 802.3by, 802.3ba, 802.3ae
- RDMA over Converged Ethernet (RoCE), hardware reliable transport, out-of-order RDMA, atomic operations
MCX653106A-ECAT• Network adapters & DPUs
NVIDIA MCX653106A-ECAT ConnectX-6 100Gb/s Dual-Port InfiniBand & Ethernet Smart Network Interface Card
High-performance dual-port 100Gb/s InfiniBand & Ethernet NIC with RDMA offloads, ideal for HPC, AI, and cloud data centers. PCIe 4.0 ready.
MCX653106A-ECAT
Product photoCMS image ready
- MCX653106A-ECAT (part of the mq9700 compatible series)
- Up to 100 Gb/s (EDR InfiniBand or 100GbE)
- PCIe 3.0/4.0 x16
- SR-IOV (Up to 1000 VFs per port)
MCX653106A-HDAT• Network adapters & DPUs
NVIDIA MCX653106A-HDAT ConnectX-6 Dual-Port 200Gb/s InfiniBand Adapter | HDR Smart NIC for HPC & AI
NVIDIA MCX653106A-HDAT ConnectX-6 dual-port 200Gb/s InfiniBand/Ethernet smart adapter.
MCX653106A-HDAT
Product photoCMS image ready
- PCIe 4.0 x16 (3.0 compatible)
- In-Network Computing: Offloads collective communication operations and memory access directly into the network
- NVIDIA GPUDirect Technologies: Direct GPU-to-GPU communication and GPU-to-storage access
- Hardware-Based I/O Virtualization (ASAP²): High-performance network isolation for virtual machines and containers
900-9X81Q-00CN-ST0
Quick quote