The GPU giant's new open architecture interconnect bridges quantum processors with classical supercomputers, and more than a dozen facilities are already on board.
Nvidia unveiled NVQLink on October 28, 2025, an open architecture interconnect designed to connect quantum processing units (QPUs) with Nvidia’s GPU-accelerated supercomputers. CEO Jensen Huang compared it to the “Rosetta Stone” for quantum-classical interplay.
What NVQLink actually does #
NVQLink delivers latency under 4 microseconds and throughput up to 400 Gb/s between GPUs and QPUs using RDMA over Ethernet. The system integrates with Nvidia’s existing CUDA-Q software platform and works across multiple quantum hardware approaches: superconducting qubits, trapped-ion systems, and photonic architectures. Each connected NVQLink system can deliver up to 40 petaflops of AI performance at FP4 with sparsity.
Quantinuum’s Helios QPU achieved real-time quantum error correction decoding 32 times faster than standard requirements when connected through NVQLink to an Nvidia GH200 Grace Hopper Superchip. The system posted a reaction time of just 67 microseconds and improved logical-qubit error rates by 5.4 times for an 8-logical-qubit memory.
Adoption is already underway #
By November 17, 2025, less than three weeks after the announcement, more than a dozen supercomputing centers globally had started working with NVQLink. Nine of those are US national laboratories.
AI, tech, and the markets they move—in one daily briefing.
Daily. Free. Join 34,000+ readers across crypto, finance, and policy.
Nvidia has assembled a coalition of 17 QPU builders and five controller vendors around the NVQLink standard.
The hybrid future Nvidia is betting on #
Nvidia’s leadership has been explicit that future GPU supercomputers will be hybridized with quantum processors. By building the bridge rather than the quantum processor itself, Nvidia avoids picking sides among quantum modalities: if superconducting qubits win, NVQLink works; if trapped ions prove superior, NVQLink works.
Disclosure: This article was edited by Diego Almada Lopez. For more information on how we create and review content, see our