Supercomputers/Systems/Condor Galaxy 3
USA · operational · ai training
Condor Galaxy 3
Operated by Cerebras at Condor Galaxy 3 site (Dallas) .
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 |
|---|---|---|---|---|---|
| Integrator | - built by Cerebras and G42 | Cerebras | - | Reported | cerebras.aicerebras.ai |
| Accelerator | Cerebras WSE-3 Accelerators Cerebras (wafer-scale) · 900,000C · TSMC N5 · 23,000 W 64 Cerebras CS-3 systems | Cerebras | 64 reported | Reported | cerebras.aig42.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 | 64 accelerators | 2024-03 | Operator stated | 64 Cerebras CS-3 wafer-scale systems (one WSE-3 each), Dallas. Counts systems, not GPUs. | cerebras.aicerebras.ai |
The read
The third Cerebras and G42 AI supercomputer, announced in March 2024 as 64 CS-3 systems on the WSE-3, with 8 exaFLOPs of AI compute and 58 million AI cores, in Dallas, Texas. Cerebras' current supercomputer page calls it built and operational but gives no date, so no first-operational date is recorded. G42 published the same announcement text, so it is not an independent second source and the tier is reported. The AI exaFLOP figure is vendor-stated on a different basis from HPL and is not recorded as FLOPS, and the AI core count is left out of the cores column. The Dallas coordinates are the city, not a facility, since no source names the data center. Condor Galaxy 2 is not recorded because we found only passing mentions in these releases and no hardware count or dedicated page.
Timeline
- 2024-03 Announced source
Site & facility
Change history
- 2026-09-20 Added Condor Galaxy 3
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 |
|---|---|---|
| cerebras.ai | names system, part and count | Cerebras WSE-3 · counts: 64 |
| cerebras.ai | names system, part and count | Cerebras WSE-3 · counts: 64 |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.