Supercomputers/Systems/MAXIMUS-384
USA · operational · ai training
MAXIMUS-384
Also known as Maximus-01
Operated by Core42 at Core42 (Lake Mariner) .
Phase 1 seed dataset, compiled by hand. These rows were built from public operator, laboratory and vendor sources. A mechanical second-reader pass has since fetched every cited source: 1092 of 1153 systems have a readable citation that names them, and 40 are genuinely weakly sourced. Every claim carries its source and a confidence tier. Treat anything below verified as a lead, not a citation.
Measured performance
- Rmax
- 114.5 PFlop/s
- Rpeak
- 251.2 PFlop/s
- Rmax ÷ Rpeak
- 45.6%
- Cores
- 976,896
- Power
- -
- Per watt
- - GF/W
Figures are as last publicly reported for the configuration described below, not a live measurement. Where a system was upgraded in place, the post-upgrade configuration is shown and the earlier one appears in the timeline.
What this machine is made of
One row per supplier relationship. “Supplier at build” is the company that shipped the part at the time; where that company has since been acquired, the parent it rolls up to today is shown beside it. That distinction is what makes ticker-level aggregation possible across a thirty-year dataset.
| Role | Part | Supplier at build | Quantity | Confidence | Source |
|---|---|---|---|---|---|
| Integrator | - Dell PowerEdge XE9680 | Dell Technologies | - | Reported | top500.org |
| Accelerator | AMD Instinct MI300X Accelerators ROCm (CDNA 3) · TSMC N5/N6 · 750 W >9,000 AMD Instinct MI300X GPUs | AMD | - | Verified | top500.orgcore42.ai |
| CPU | Intel Xeon Platinum 8570 CPUs x86-64 · 56C · 2.1 GHz · Intel 7 Xeon Platinum 8570 56C | Intel | - | Reported | top500.org |
| Interconnect | Broadcom RoCE Ethernet Interconnect RoCE over Broadcom silicon, Arista Networks EOS switches | Broadcom | - | Verified | top500.orgcore42.ai |
AI datacenter metrics
Figures beyond an accelerator count, each with who stated it. What can and cannot be compared across AI datacenters.
| Metric | Value | As of | Basis | Note | Source |
|---|---|---|---|---|---|
| Accelerators | 9,000 accelerators | 2025-11 | Operator stated | Core42 release (18 Nov 2025): more than 9,000 AMD MI300X GPUs at Lake Mariner, Buffalo (value is the floor). | core42.ai |
The read
Core42's own branding calls this cluster Maximus-01; TOP500 and wire-service headlines both also use MAXIMUS-384, so both names are recorded. Over 9,000 AMD Instinct MI300X GPUs at TeraWulf's Lake Mariner data center campus, networked on Broadcom silicon and Arista switches. The press release is widely syndicated but traces to one source, so this stays at reported rather than verified tier.
Timeline
- 2025-11 Announced source
- 2025-11 First operational source
- 2026-06 List debut at #24 (June 2026) source
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Site & facility
Source check
We fetched this system's own citations and recorded whether each page actually mentions it. This is a corroboration signal, not a fact check, and it is published so you can see how well the sourcing holds up rather than take it on trust.
| Cited source | Result | Found on the page |
|---|---|---|
| top500.org | names system and part | AMD Instinct MI300X, Intel Xeon Platinum 8570 |
| core42.ai | names system and part | AMD Instinct MI300X, Broadcom RoCE Ethernet |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.
Further reading
Inside a node
Why accelerators exist, what the memory hierarchy costs, and how the CPU and accelerator merged onto one package.
The interconnect
Topologies, why latency and tail behaviour matter more than bandwidth, and how the fabric market consolidated.
Operating a supercomputer
Acceptance testing, why "installed" and "in production" are six months apart, and the machine lifecycle.