Marlowe (Stanford)

Also known as Marlowe

Operated by Stanford University at Stanford Research Computing Center .

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: -
Rpeak: -
Rmax ÷ Rpeak: -
Cores: -
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
Accelerator	NVIDIA H100 SXM5 Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W 248 NVIDIA H100 GPUs in an NVIDIA DGX H100 SuperPOD	NVIDIA NVDANASDAQ	248 reported	Reported	ee.stanford.edu nvidia.com
Interconnect	NVIDIA InfiniBand NDR (Quantum-2) Interconnect Fat tree or dragonfly+ · 400 Gb/s per port · Under 0.6 microseconds NVIDIA Quantum-2 InfiniBand	NVIDIA NVDANASDAQ	-	Reported	nvidia.com
Storage	DDN EXAScaler Storage Lustre appliance 2.5 PB DDN ExaScaler Lustre plus 3 PB DDN IntelliFlash	DDN	-	Reported	marlowe-research.stanford.edu

The read

Stanford's first GPU-based supercomputer, an NVIDIA DGX H100 SuperPOD with 248 H100 GPUs, operated by Stanford HAI in partnership with Stanford University IT and the Vice Provost for Research, per its user guide. Stanford's news piece says it was installed in summer 2024 on a university investment of $30 million and opened to applications on 15 January 2025; NVIDIA's case study confirms 248 Hopper GPUs, Quantum-2 InfiniBand and a primary focus on large-scale AI model training, with more than 500 active research accounts. The user guide (marlowe-research.stanford.edu) lists 2.5 PB of DDN ExaScaler Lustre and 3 PB of IntelliFlash storage and says the system ranked 87th on the June 2024 TOP500 at 11.1 PFlops; we did not fetch a TOP500 entry, so no list appearance or FLOPS is recorded and ranked stays 0. The site is Stanford's research computing data center as the news piece describes it, using the campus-level record already in the dataset. NVIDIA names Mark III Systems as the integrator, but no integrator edge is recorded because the company is not yet in the dataset.

Timeline

2024-12 Announced source

Site & facility

Stanford Research Computing Center

Location: Stanford, CA, USA
Commissioned: 2014

sherlock.stanford.edu srcc.stanford.edu

Change history

2026-10-02 Marlowe (Stanford) added (DGX H100 SuperPOD, 248 H100)

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
ee.stanford.edu	names system, part and count	NVIDIA H100 SXM5 · counts: 248
nvidia.com	blocked our fetch	-

Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.