Technology

NVIDIA Quantum-X800

NVIDIA's InfiniBand XDR platform — Q3400-RA switch plus ConnectX-8 SuperNICs — doubling per-port bandwidth to 800 Gbps with 144 ports per switch and 9× more in-network compute (14.4 Tflops via SHARPv4) than the NDR generation.

9 connections3 resources1 post

Summary

What it is

Where it fits

The fabric under the 2026 rack-scale deployments: CoreWeave's industry-first Vera Rubin NVL72 bring-up (June 1, 2026) and Azure's GB200 clusters both ride Quantum-X800. Because GPUDirect and S3-over-RDMA share this fabric, its port speed is the ceiling on what object storage can deliver into GPU HBM. The Spectrum-X800 Ethernet sibling is NVIDIA hedging the Ethernet-vs-InfiniBand split.

Misconceptions / Traps

Deployment numbers are vendor-published (CoreWeave's 10× cost-per-million-tokens claim included); independent measurements vs NDR are scarce.
XDR does not make the fabric decision for you — Dell'Oro projects Ethernet overtakes InfiniBand in AI back-ends by 2027, so this is the premium-latency fork, not the default.

Key Connections

implements RDMA (RoCE v2 / InfiniBand) — the IBTA 2.0 XDR baseline
integrates_with NVIDIA GPUDirect RDMA for S3 — the S3-to-HBM path rides this fabric
enables KV-Cache Disaggregation — sets the KV-transfer bandwidth budget
competes_with Ultra Ethernet (UEC) — the InfiniBand side of the fabric fork

Definition

What it is

NVIDIA's flagship InfiniBand XDR (eXtreme Data Rate) networking platform — the Q3400-RA switch plus ConnectX-8 SuperNICs — doubling per-port bandwidth over the previous NDR generation from 400 Gbps to **800 Gbps per port**. The platform provides 144 ports of 800 Gbps connectivity and a 9× increase in in-network computing capacity (14.4 Tflops via SHARPv4) versus NDR. Its Ethernet sibling, **Spectrum-X800**, carries RoCEv2 with proprietary enhancements and deploys alongside InfiniBand in the same facilities at up to 1.6 Tb/s of backend bandwidth per GPU in non-blocking multi-rail topologies.

Why it exists

As GPU compute density scales, the fabric between compute nodes and storage targets became the primary bottleneck. XDR exists to keep rack-scale architectures (GB200, Vera Rubin NVL72) fed — and because S3-over-RDMA and GPUDirect Storage ride the same fabric, every doubling of port bandwidth directly raises the ceiling on what an object-storage tier can deliver to GPU HBM.

Primary use cases

AI back-end networks for rack-scale GPU architectures, KV-cache transfer between disaggregated prefill/decode pools, GPUDirect RDMA paths from S3-compatible storage into GPU memory, in-network reduction via SHARPv4 for distributed training.

Recent developments

Latest signals

CoreWeave brought the first NVIDIA Vera Rubin NVL72 online over Quantum-X800 (June 1, 2026). The first AI cloud provider to bring the rack-scale Vera Rubin architecture online used Quantum-X800 InfiniBand to connect the nodes (vendor-published deployment data). CoreWeave claims the deployment delivers up to 10× lower cost per million tokens for agentic inference versus earlier Blackwell deployments (vendor-published claims). Per CoreWeave — industry-first Vera Rubin NVL72 bring-up.
Microsoft Azure deploys Quantum-X800 for GB200 Superchip clusters. Azure announced Quantum-X800 fabric deployments supporting its GB200 clusters, extending parallel computing tasks across massive GPU scale (vendor-published). Per Microsoft Azure — Microsoft and NVIDIA partnership.
The platform numbers: 144× 800 Gbps ports, SHARPv4 at 14.4 Tflops in-network compute (9× NDR). Vendor-published hardware metrics for the Q3400-RA switch + ConnectX-8 SuperNIC combination. Per Introl — InfiniBand switches: Quantum-X800, XDR, SHARP and NVIDIA — switch announcements.
Where the Ethernet sibling fits. Spectrum-X800 is NVIDIA's answer to keeping RoCEv2 workloads on NVIDIA silicon while the market splits between InfiniBand (latency-sensitive, tightly coupled training) and Ethernet (cost, supply-chain diversity, no proprietary lock-in). Dell'Oro projects Ethernet surpasses InfiniBand in AI back-end networks by 2027 (independent-methodology market forecast) — this platform is NVIDIA holding both sides of that bet. Per Nokia — future of AI networking with UEC (citing Dell'Oro).