Argonne flexes spare supercompute to build private AI inference servic
Jump to main content
REG AD
ai + ml
Argonne flexes spare supercompute to build private AI inference service Think ChatDoE
Tobias Mann Tobias Mann
Systems editor
Published wed 27 May 2026 // 21:15 UTC
Boffins at the Department of Energy’s (DoE) Argonne National Laboratory near Chicago on Tuesday unveiled a new AI inference service cobbled together from spare supercomputing capacity.The hope is that the service can help researchers across the US, including DoE labs and those working on the Genesis Mission, advance scientific discovery across a range of fields.Argonne is home to some of the world’s largest supercomputing clusters, including the No. 3-ranked Aurora supercomputer. But its compute capacity also includes several smaller, AI-optimized systems.
REG AD
As of writing, the lab’s inference service is running atop two clusters: The first is the Sophia system, comprising 192 Nvidia A100 GPUs, most with 40 GB of memory. The second, dubbed Metis, is arguably the more interesting. That system features 32 of SambaNova’s SN40L AI accelerators.
REG AD
Moving forward, Argonne says that the inference service will also be extended to the Nvidia GH200-based Tara and B200-based Minerva systems.The inference service provides researchers with access to a range of large language models (LLMs) through a chatbot-like portal. Models include OpenAI's GPT-OSS, Google’s Gemma family, Meta’s Llama herd, and a variety of domain-specific and custom models, like AuroraGPT. And at least for some of its services, Argonne appears to be using Open WebUI, a popular self-hosted chatbot service we’ve explored on numerous occasions.Argonne envisions researchers harnessing these models to securely analyze large datasets and experiment with integrating generative AI into their workflows.“By making AI inference available as a shared resource, we are enabling researchers to apply AI at scale to their data, their simulations and their experiments without having to build and maintain their own infrastructure,” ALCF director Michael Papka said in a statement.Critically, the service enables DoE researchers to experiment with chatbots in a secure manner that doesn’t expose data to public services like ChatGPT.According to Argonne, researchers are already using the service to analyze experimental data in real time to predict things like plasma disruptions in fusion energy research. Boffins are also using the tech to sift through large quantities of data generated by particle accelerators and telescopes to narrow the search radius of the most likely candidates. By doing so, researchers can make better use of available supercomputing capacity, rather than wasting cycles brute forcing the problem.
REG AD
MORE CONTEXT GPU behemoth Nvidia on track to be world's leading CPU supplier too, says CFO
AMD says its $4K Ryzen AI Halo workstation practically pays for itself
Uncle Sam's next big supercomputer might use something more exotic than GPUs
France buys nuclear supercomputing spinoff Bull from Atos for €404M
While LLMs and other generative AI models still struggle with hallucinations and other erroneous behavior, there’s a growing corpus of research to suggest that the technology can be used to automate research or supplement traditional climate or physics models.For example, before it was air-gapped, the eggheads at Lawrence Livermore National Laboratory tasked El Capitan, the world's most powerful publicly known supe, to develop a new tsunami forecasting model. Meanwhile, Nvidia has demonstrated that AI climate models can identify storm cells faster and more accurately than existing models. ®
argonne national laboratory supercomputing department of energy ai + ml ai large language models ai inference
REG AD
public sector
ICE to keep an eye on your eyes under $25M biometric scanner deal
And you thought a face recognition app was intrusive?
Security
No fix yet for critical RCE bug in open-source Git service Gogs - exploit module is out
Researcher reported the vuln in March. Maintainers haven't responded to his messages since
PARTNER CONTENT
AI and data sovereignty in Postgres: An answer to the datacenter energy crisis
A billion AI agents walk into a power grid
Legal
23andMe inherits lawsuit over 'disturbing' DNA data breach
California AG claims genetics biz downplayed 2023 mega-leak while paying ransom to attacker
Systems
EU's digital sovereignty boo-boo may be the best thing to ever happen to the project
DIY or die. Just don't let the CIA buy it
software
UCLA seeks pre-litigation resolution with Oracle
Discussion understood to concern delayed SaaS transformation project
MOST POPULAR
AI + ML Google has seriously leaned into AI enshittification lately Security Anthropic to release Mythos-class models to the public Security Disgruntled 0-day hunter 'humiliated' by Microsoft pledges 'bone shattering drop' as Redmond calls cops