- Odinn Infinity Cube combines multiple Omnia supercomputers in a single glass enclosure
- Memory capacity reaches 86TB of registered DDR5 ECC RAM
- NVMe storage in the cube totals 27.5 PB
Odinn, a California-based startup, introduced the Infinity Cube as an attempt to compress data center-class computing into a visually contained structure.
At CES 2026, the company unveiled the Odinn Omnia, a mobile AI supercomputer, although a system of this scale alone would face obvious throughput limitations, and that’s where the Cube comes in.
The Infinity Cube is a 14ft x 14ft AI cluster capable of assembling multiple Omnia AI supercomputers into a single glass enclosure.
Scaling AI with Modular Clustering
This device emphasizes extreme component density rather than incremental improvements in efficiency.
According to Odinn, a fully customizable base specification allows the Cube to scale up to 56 AMD EPYC 9845 processors, packing 8960 processor cores.
Its GPU capacity expands to 224 Nvidia HGX B200 units, paired with 43TB of combined VRAM.
For storage, the device supports up to 86TB of registered DDR5 ECC RAM, while the NVMe storage capacity reaches 27.5PB.
These figures imply significant internal electricity interconnection and distribution demands that the company has not detailed publicly.
The device uses liquid cooling, with each Omnia unit managing its own thermal needs without shared external infrastructure.
This design avoids the need for raised floors or centralized cooling installations, at least in theory.
The Infinity Cube relies on a proprietary software layer called NeuroEdge to coordinate workloads across the cluster.
The software integrates with Nvidia’s AI software ecosystem and common frameworks, automatically managing planning and deployment.
This abstraction aims to reduce the need for manual tuning, although it also places an operational dependency on Odinn’s software maturity.
Institutions that already rely on cloud infrastructure for AI workloads may wonder whether local orchestration simplifies administration in real-world conditions.
The company says the Infinity Cube is suitable for organizations with strict privacy, security or latency requirements that discourage reliance on the cloud.
Bringing infrastructure closer to workloads can reduce network delays, but it also shifts responsibility for availability, maintenance, and lifecycle management to the owner.
The idea of ​​presenting data center hardware in compact glass enclosures can be aesthetically pleasing.
However, the practical tradeoffs between density, accessibility, and resilience remain unresolved without evidence of real-world deployment.
TechRadar will cover this year’s events extensively THESEand will bring you all the big announcements as they happen. Visit our CES 2026 News for the latest stories and our hands-on verdicts on everything from wireless TVs and foldable displays to new phones, laptops, smart home gadgets and the latest in AI. You can also ask us a question about the show in our Live Q&A from CES 2026 and we will do our best to answer them.
And don’t forget to follow us on TikTok And WhatsApp for the latest news from the CES show!
