Google · TPU · Layer 2
Google TPU v7 (Ironwood)
Inference at scale on Google Cloud. Ships in 256-chip and 9,216-chip configurations.
cloud only Cannot be bought. Exists only inside one cloud, so choosing it is choosing that cloud.
Specifications
- Memory
- 192 GB HBM3E per chip
- Bandwidth
- 7.37 TB/s per chip
- Compute
- 4,614 FP8 TFLOPS per chip
- Power
- Not published
- Interconnect
- 9.6 Tb/s inter-chip (ICI)
- Software
- JAX, XLA, PyTorch/XLA
- Form factor
- accelerator
- Workload
- inference
Verified 2026-09-09. Fields reading “not published” are exactly that — we do not estimate a figure a vendor withholds.
The catch
You cannot buy this. It exists only inside Google Cloud, so choosing it is choosing a cloud, permanently. It is also inference-optimised — do not benchmark it as a training part.
The economics
Vertically integrated: the price you see is a cloud price, not a chip price, and it is not comparable to a $/GPU-hour rental line.
Cost per million tokens is the metric that decides most real purchases, and there is no neutral benchmark for it — every published figure comes from a company selling one side of the comparison. Read all of them, ours included, as claims rather than measurements.
The power question underneath this
A rack of frontier accelerators draws 120–200 kW against a 2026 average of about 27 kW, and the US grid interconnection queue exceeds 2,600 GW with waits approaching five years. Whether you can energise this part is now a harder question than whether you can buy it.
Layer 1 — Energy · The interconnection queue · Rack power density · Tokens per watt
Where you actually rent this
Choosing the part is the easy half. The same accelerator rents for wildly different money depending only on who you rent it from — the cheapest and dearest published on-demand price for an H100 sit 5.6× apart — and the provider, not the chip, is what decides whether you can leave later.
Compared against
- Google TPU v7 (Ironwood) vs AWS Trainium 3 — Two chips you cannot buy. This is a cloud commitment dressed as a hardware comparison.Compare with AWS Trainium 3
- NVIDIA GB200 NVL72 vs Google TPU v7 (Ironwood) — Rack-scale coherent memory against a 9,216-chip inference pod. Different shapes of the same bet.Compare with NVIDIA GB200 NVL72
- Google TPU v6e (Trillium) vs Google TPU v7 (Ironwood) — One generation apart, and Google publishes far more detail about the newer one — which is itself a signal about how they want them compared.Compare with Google TPU v6e (Trillium)
Related silicon
- Google TPU v6e (Trillium) — Not published in directly comparable terms, cloud only
- AWS Inferentia 2 — Not published in directly comparable terms, cloud only
- AWS Trainium 2 — Not published in directly comparable terms, cloud only
- AWS Trainium 3 — 144 GB HBM3e per chip, cloud only
- Cerebras WSE-3 — 44 GB on-chip SRAM, rent
- Groq LPU — 230 MB SRAM per chip, no HBM, rent
Sources
Want this whole layer as one table?
The accelerators on these pages as a single CSV — memory, bandwidth, compute, power, interconnect, software stack, availability, who each part is for and the catch — ready to sort, filter or load into a notebook.
Get the silicon table — free for research and evaluation
Four short lines and the download starts at once (CC-BY-NC-4.0, built from these pages the moment you ask). What you type is used only to answer the request and is never sold. Prefer Hugging Face? Request it there.
Using it inside a product, a client report or anything you sell? That needs a commercial licence.