Google TPU7x (Ironwood) Pod
A full TPU7x (Ironwood) pod is 9,216 chips in a 3D torus, the largest TPU pod Google has built. Per chip Google publishes 2,307 TFLOPS bf16 and 4,614 TFLOPS fp8, giving 21.26 EFLOPS and 42.52 EFLOPS across the pod; the fp8 total matches the 42.5 exaflops Google has stated publicly for an Ironwood pod, which independently confirms that chip count times per-chip peak is Google's own arithmetic. Memory is 9,216 x 192 GiB HBM at 7,380 GBps per chip, for 1.77 PB of HBM and 68 PB/s of aggregate memory bandwidth. Supported slice shapes go up to 8x16x16, or 2,048 chips, within the pod. No int8 figure is published. The table lists four SparseCores per chip; those are embedding-lookup dataflow processors, not weight sparsity. Google publishes no sparse figures and no pod-level power.
We will point you at suppliers who have it. Free, and no signup.
System Details
GPU Configuration
System Specifications
Precision Performance Breakdown
| Precision | System Performance | Per GPU | Efficiency |
|---|---|---|---|
| 21261.312 PFLOPS | 2307.0 TFLOPS | — | |
| 42522.624 PFLOPS | 4614.0 TFLOPS | — |
All figures are dense. Vendors commonly headline the number, which is twice the dense one.
Powered by Google TPU v7
This system utilizes 9216 × Google TPU v7 192GB GPUs, each delivering exceptional performance for AI and HPC workloads.
Per GPU TDP
—
Per GPU Memory
192 GB
Process Node
—
Architecture
TPU
Documentation & Resources
Official Datasheet
Google TPU7x (Ironwood) Pod technical specifications
Cloud TPU v5p
Google • 2023-12-07
Typical Use Cases
The Google TPU7x (Ironwood) Pod runs 9216× TPU v7 GPUs over 3D torus ICI, 1,200 GBps bidirectional per chip, delivering 42,523 PFLOPS FP8 dense.