DEPLOYDatabase

Chip comparison

Google TPU v5e vs Google TPU v5p

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 v5eGoogle TPU v5p
TDP170 W300 W
Memory16 GB HBM295 GB HBM2e
Memory bandwidth819 GB/s2,765 GB/s
BF16 (dense)197 TFLOPS459 TFLOPS
INT8 (dense)393 TOPS918 TOPS
Form factorOAM (v5e pod, up to 256 chips)OAM (per-chip in v5p pod)
Announced2023-08-292023-12-06
Released2023-11-012024-01-01

Robots running Google TPU v5e

No robots publicly running it yet.

Robots running Google TPU v5p

No robots publicly running it yet.

Data centers with Google TPU v5p

Common questions

Google TPU v5e vs Google TPU v5p: which is faster for training?

Google TPU v5p has 2.33x the dense FP16/BF16 throughput of the other (Google TPU v5e: 197 TFLOPS; Google TPU v5p: 459 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

Google TPU v5e vs Google TPU v5p: which has more memory?

Google TPU v5p carries more HBM (Google TPU v5e: 16 GB HBM2; Google TPU v5p: 95 GB HBM2e). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

Google TPU v5e vs Google TPU v5p: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Google TPU v5e 1.16 (197 ÷ 170 W); Google TPU v5p 1.53 (459 ÷ 300 W). Google TPU v5p wins at the die level; system-level efficiency also depends on cooling and interconnect.

See also: every chip comparison · Google TPU v5e full page · Google TPU v5p full page.