Supercomputers/Systems/Google TPU7x (Ironwood) pod
USA · operational · ai training
Google TPU7x (Ironwood) pod
Operated by Alphabet at Google Cloud (undisclosed location) .
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 | Google TPU7x (Ironwood) Accelerators TPU (systolic array) TPU7x (Ironwood): 9216 chips per pod | Alphabet | 9,216 reported | Reported | cloud.google.com |
| Interconnect | Google TPU inter-chip interconnect (3D torus) Interconnect 3D torus · 1,200 GB/s bidirectional per chip (v5p and TPU7x) TPU inter-chip interconnect (ICI), 3D torus scaling to 9216 chips | Alphabet | - | Reported | cloud.google.com |
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 | 9,216 accelerators | 2026-10 | Operator stated | Google Cloud docs: 9,216-chip footprint per TPU7x (Ironwood) Pod; undated product documentation, one documented pod configuration not a site | docs.cloud.google.com |
The read
A Google Cloud TPU7x (Ironwood) pod of 9,216 chips on a 3D torus, at 4,614 TFLOPs FP8 and 2,307 TFLOPs BF16 peak per chip and 192 GiB of HBM, the largest pod Google documents. Google documents the pod as a product configuration and does not say where any pod is installed or how many exist, so this row is one documented pod, not an installation; USA records only the operator's home country. It publishes per-chip peak figures and no aggregate, and we do not multiply them into a pod-level FLOPS figure, so the row carries no FLOPS. Everything here rests on Google's own undated documentation.
Timeline
No dated events recorded.
Site & facility
Change history
- 2026-09-20 Google TPU7x Ironwood pod added (product configuration, no site disclosed)
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 |
|---|---|---|
| cloud.google.com | names system, part and count | Google TPU7x (Ironwood), Google TPU inter-chip interconnect (3D torus) · counts: 9216 |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.
Related news
- Google's Ironwood (TPU v7) becomes generally available, compared directly to El Capitan · GoogleGoogle's own launch materials put a full Ironwood pod at 42.5 exaflops of FP8 compute, described as more than 24x El Capitan's 1.7 exaflops figure, though the two numbers measure different things, dense FP8 inference throughput versus double precision HPL, and are not a like for like comparison. It is nonetheless the most direct public benchmark claim yet tying a hyperscaler's own accelerator generation to a specific system already in this dataset.