Supercomputers/Systems/Condor Galaxy 1
USA · operational · ai training
Condor Galaxy 1
Operated by Cerebras at Colovore (Santa Clara) .
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 | Cerebras CS-2 (WSE-2) Accelerators Cerebras (wafer-scale) 64 Cerebras CS-2 systems | Cerebras | 64 reported | Verified | 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 | 2023-07 | Operator stated | 64 Cerebras CS-2 wafer-scale systems (one WSE-2 each), Santa Clara. Counts systems, not GPUs. | cerebras.aig42.ai |
The read
The first Cerebras and G42 AI supercomputer, 64 CS-2 systems in Santa Clara, announced in July 2023 with half the systems running and declared complete in November 2023. Cerebras built and operates it and G42 Cloud offers it. Both companies state the 64 systems and the site, but G42's release repeats Cerebras' text, so the tier is reported. Cerebras quotes 4 exaflops of 16-bit AI compute, an operator-stated figure on a different basis from HPL, so it is not recorded as FLOPS. Cerebras' own material gives the fabric as both 388 and 386 Tb/s. Condor Galaxy 2 and 3 are not recorded, because only one release each supports them.
Site & facility
Change history
- 2026-09-20 Added from operator sources
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 CS-2 (WSE-2) · counts: 64 |
| g42.ai | blocked our fetch | - |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.