DEPLOYDatabase

Chip comparison

Google TPU v7 (Ironwood) vs NVIDIA A10 Tensor Core GPU

Side-by-side specs

Straight from each vendor's datasheet. Winner in bold: higher throughput, memory, or transistor count; lower power draw or price. Sparse (2:4) throughput roughly doubles the FP8/INT8 numbers shown.

FieldGoogle TPU v7 (Ironwood)NVIDIA A10 Tensor Core GPU
Process nodeSamsung 8N
Transistors (B)28.3
Die size628 mm²
TDP700 W150 W
Memory192 GB HBM3e24 GB GDDR6
Memory bandwidth7,400 GB/s600 GB/s
FP16 (dense)125 TFLOPS
BF16 (dense)4,614 TFLOPS125 TFLOPS
FP8 (dense)9,228 TFLOPS
INT8 (dense)250 TOPS
Form factorOAM (Ironwood pod, up to 9,216 chips)PCIe
Announced2025-04-092021-04-12
Released2025-12-012021-04-12

Robots running Google TPU v7 (Ironwood)

No robots publicly running it yet.

Robots running NVIDIA A10 Tensor Core GPU

No robots publicly running it yet.

Data centers with Google TPU v7 (Ironwood)

No data centers publicly running it yet.

Data centers with NVIDIA A10 Tensor Core GPU

No data centers publicly running it yet.

Common questions

Google TPU v7 (Ironwood) vs NVIDIA A10 Tensor Core GPU: which is faster for training?

Google TPU v7 (Ironwood) has 73.82x the dense FP16/BF16 throughput of the other (Google TPU v7 (Ironwood): 9,228 TFLOPS; NVIDIA A10 Tensor Core GPU: 125 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

Google TPU v7 (Ironwood) vs NVIDIA A10 Tensor Core GPU: which has more memory?

Google TPU v7 (Ironwood) carries more HBM (Google TPU v7 (Ironwood): 192 GB HBM3e; NVIDIA A10 Tensor Core GPU: 24 GB GDDR6). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

Google TPU v7 (Ironwood) vs NVIDIA A10 Tensor Core GPU: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Google TPU v7 (Ironwood) 13.18 (9,228 ÷ 700 W); NVIDIA A10 Tensor Core GPU 0.83 (125 ÷ 150 W). Google TPU v7 (Ironwood) wins at the die level; system-level efficiency also depends on cooling and interconnect.

See also: every chip comparison · Google TPU v7 (Ironwood) full page · NVIDIA A10 Tensor Core GPU full page.