IBM, NVIDIA, and Fermilab to Build Co-Design Platform for Modular Quantum Computers

iconCryptoBriefing
Share
AI summary iconSummary
IBM, NVIDIA, and Fermilab announced on November 16, 2026, a co-design platform to boost modular quantum computing. The project combines IBM’s 120-qubit Quantum Nighthawk processor with NVIDIA’s DGX B200 systems, while Fermilab’s SQMS Center handles interconnects and scalability. NVIDIA also released TCBP-JOBS, a decoding algorithm that claims to cut computation times by up to 13,000x. The partnership follows IBM’s 2024 deal with Fermilab and NVIDIA’s CUDA-Q work. On-chain news highlights the growing role of quantum computing in blockchain and new token listings.

IBM, NVIDIA and Fermi National Accelerator Laboratory announced plans on November 16, 2026 to build a co-design platform aimed at speeding up development of modular quantum computers.

The platform is built around two flagship pieces of hardware. One comes from each corporate partner.

What’s actually going into the lab

On the quantum side sits IBM’s Quantum Nighthawk, a 120-qubit processor. IBM says it can run circuits containing up to 7,500 two-qubit operations, at speeds that can reach 100,000 samples per second.

On the classical side, NVIDIA is contributing its DGX B200 systems. These are the same class of accelerated computing machines that power large AI workloads, now drafted into helping quantum chips do their jobs.

Fermilab’s role runs through its Superconducting Quantum Materials and Systems (SQMS) Center. The center will test and develop ways to connect multiple quantum processors together, and to scale up classical computing resources as the quantum side grows.

The partners say the work will focus on error correction, scalable architectures and scientific applications. The target fields are high-energy physics and nuclear physics.

The decoder that steals the show

Alongside the announcement, NVIDIA unveiled a new decoding algorithm called TCBP-JOBS. It is designed for quantum error-correction research.

The numbers attached to it are eye-catching. NVIDIA says the algorithm could cut certain computation times from 12 weeks down to 45 minutes, a speedup of up to 13,000x.

Note the qualifiers, though. The 13,000x figure is an upper bound, and the 12-weeks-to-45-minutes comparison applies to certain tasks.

Not the first date for these partners

This collaboration builds on relationships already in place. IBM’s partnership with Fermilab’s SQMS Center was formalized in 2024.

NVIDIA, meanwhile, has been building out its CUDA-Q software for quantum work. Its CUDA-Q Logical release arrived in September 2026, and the new platform leans on those capabilities.

IBM has also been busy elsewhere. Earlier in November 2026, it was tied to a collaboration with Oak Ridge National Laboratory and AMD, another pairing of quantum hardware with a national lab and a classical chipmaker.

What this means

For IBM, the deal places Nighthawk inside a working research environment with real scientific users. For Fermilab, the payoff is access to tools that could accelerate research in its core fields. The SQMS Center also gets a hands-on role in solving the interconnect problem for modular quantum computers.

Investors watching IBM and NVIDIA should keep expectations grounded. This is a plan for a platform, not a commercial product launch, and the headline speedups come with “up to” and “certain tasks” attached.

Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information. Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.