logo
Home Cases

IBM Quantum Co-Design Platform With Fermilab and NVIDIA Targets Modular Systems, Plus a 79x Accuracy Gain on Fe4S4

Certification
China Beijing Qianxing Jietong Technology Co., Ltd. certification
China Beijing Qianxing Jietong Technology Co., Ltd. certification
Customer Reviews
The sales staff of Beijing Qianxing Jietong Technology Co.,Ltd are very professional and patient. They can provide quotations quickly. The quality and packaging of the products are also very good. Our cooperation is very smooth.

—— 《Festfing DV》LLC

When I was looking for intel CPU and Toshiba SSD urgently, Sandy from Beijing Qianxing Jietong Technology Co., Ltd gave me a lot of help and got me the products I needed quickly. I really appreciate her.

—— Kitty Yen

Sandy of Beijing Qianxing Jietong Technology Co.,Ltd is a very careful salesman, who can remind me of configuration errors in time when I buy a server. The engineers are also very professional and can quickly complete the testing process.

—— Strelkin Mikhail Vladimirovich

We are very happy with our experience working with Beijing Qianxing Jietong. The product quality is excellent, and delivery is always on time. Their sales team is professional, patient, and very helpful with all our questions. We truly appreciate their support and look forward to a long-term partnership. Highly recommended!

—— Ahmad Navid

Quality: “Great experience with my supplier. The MikroTik RB3011 was already used, but it was in very good condition and everything works perfectly. Communication was fast and smooth, and all my concerns were addressed quickly. Very reliable supplier—highly recommended.”

—— Geran Colesio

I'm Online Chat Now

IBM Quantum Co-Design Platform With Fermilab and NVIDIA Targets Modular Systems, Plus a 79x Accuracy Gain on Fe4S4

November 18, 2026

IBM, Fermilab, and NVIDIA plan to build a modular quantum computing co-design platform that pairs NVIDIA DGX B200 systems with IBM quantum hardware, including units powered by the IBM Quantum Nighthawk processor. This work follows a prior co-design initiative focused on quantum error correction, and targets the modular layouts IBM envisions for future fault-tolerant quantum machines. IBM also outlined new Slurm integration to schedule quantum processors, alongside a chemistry simulation result with RIKEN that the team states is 79 times more precise than its earlier trial.


latest company case about IBM Quantum Co-Design Platform With Fermilab and NVIDIA Targets Modular Systems, Plus a 79x Accuracy Gain on Fe4S4  0


Co-Designing Quantum and Classical Infrastructure


NVIDIA’s portion of this collaboration covers a fresh error-correction decoder, while IBM’s announcement adds details on Fermilab’s role. The effort leverages the lab’s Superconducting Quantum Materials and Systems (SQMS) Center, which supplies ultracoherent superconducting cavities, candidate interconnects, quantum memory modules, and bosonic resources. Anna Grassellino, Fermilab chief technology officer and director of the SQMS Center, highlighted “SQMS expertise in ultracoherent quantum hardware” as the institute’s core contribution to the joint project.


IBM notes researchers will leverage the platform to test requirements for multi-processor quantum operation, run large sampling workloads, and scale classical computing resources alongside quantum hardware. The scope covers emerging scientific use cases, tight integration of supercomputing and quantum assets, and component development for next-generation quantum systems. Fermilab and IBM additionally intend to explore calculations for high-energy and nuclear physics, such as lattice gauge theories, neutrino interaction modeling, and nuclear simulations. IBM has not shared the deployment location, hardware quantity, or target launch timeline.


On the quantum side, IBM describes Nighthawk as its most capable processor built to date. It supports circuits with up to 7,500 two-qubit operations across 120 qubits, at sampling rates reaching 100,000 samples per second. IBM reports the current Nighthawk r2 delivers 25 times the throughput of its Heron processor. The firm maintains a published quantum hardware roadmap, though it has not specified which Nighthawk revision will be deployed on this co-design platform.


Slurm Scheduling for Shared Quantum Processors


IBM, NVIDIA and Pasqal collaborated with the open-source community to bring quantum computers into standard supercomputing workflows via the Quantum Resource Management Interface (QRMI), a vendor-neutral open software layer. QRMI now connects directly to Slurm’s Hierarchical Resources (HRES) scheduling capability. Slurm originally lacked native support for quantum processors, so research facilities previously accessed QPUs through custom plugins.


A single QPU can be shared across multiple compute nodes. HRES lets administrators treat it as a shared resource and enforce usage limits for separate workload partitions. Slurm can then allocate, reserve, and track QPU consumption under scheduling rules already adopted by HPC centers, letting researchers request quantum resources directly within job scripts. IBM did not specify a particular Slurm release version, while NVIDIA — which acquired Slurm developer SchedMD — has announced upcoming platform support for QRMI and QDMI.


Quantum-Classical Simulation of an Iron-Sulfur Cluster


Scientists from IBM, RIKEN and NVIDIA used sample-based quantum diagonalization (SQD) to study Fe4S4, an iron-sulfur cluster whose strongly coupled electrons create tough simulation challenges. The team began with a deliberately approximate yet physically realistic guess of the molecule’s state, guiding the quantum hardware toward the relevant electron configurations. Classical computation ran on NVIDIA GPUs, including RIKEN’s ROQUO supercomputer, which IBM confirms is constructed from NVIDIA GB200 NVL4 systems.


The team executed circuits with up to 4,000 two-qubit operations over 72 qubits and gathered 5 million measurement samples. IBM reports 79-fold better accuracy than prior runs of this same experiment, with results falling within 4.3 millihartree of outputs from density-matrix renormalization group (DMRG), the classical method used as the benchmark. These performance figures are provided by the vendors; independent validation or auditing was not completed for this write-up. IBM has not named the specific quantum processor used for this simulation.


This work is separate from the protein-ligand modeling study by IBM, RIKEN and the Cleveland Clinic, a finalist for the 2026 ACM Gordon Bell Prize that NVIDIA featured at the conference and which also relied on ROQUO. The Fe4S4 research receives backing from Japan’s New Energy and Industrial Technology Development Organization (NEDO) through its hybrid quantum-supercomputing platform program.


Decoder and HPC Results at SC26


Among related work IBM presented at SC26, Pelagos is an open-source decoder project co-developed by IBM and AMD, built atop the Triton framework and compatible with both AMD and NVIDIA GPUs. IBM states its decoder benchmarks reached speeds up to 97 times faster than a single CPU core, and GPU decoding performance scaled 7.5 times across eight AMD Instinct accelerators relative to one accelerator on ORNL’s HPE Lux AI cluster. Researchers from the University of Illinois Urbana-Champaign, NCSA and IBM also linked NCSA’s DeltaAI supercomputer to an IBM quantum system to simulate Cu3C6O6, a kagome-lattice metal.


Beijing Qianxing Jietong Technology Co., Ltd.
Sandy Yang/Global Strategy Director
WhatsApp / WeChat: +86 13426366826
Email: yangyd@qianxingdata.com
Website: www.qianxingdata.com/www.storagesserver.com
Business Focus:
ICT Product Distribution/System Integration & Services/Infrastructure Solutions
With 20+ years of IT distribution experience, we partner with leading global brands to deliver reliable products and professional services.
“Using Technology to Build an Intelligent World”Your Trusted ICT Product Service Provider!

Contact Details
Beijing Qianxing Jietong Technology Co., Ltd.

Contact Person: Ms. Sandy Yang

Tel: 13426366826

Send your inquiry directly to us (0 / 3000)