DEPLOYDatabase

Chip comparison

Google TPU v4 vs NVIDIA Jetson AGX Orin

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 v4NVIDIA Jetson AGX Orin
Process nodeTSMC N7Samsung 8N
TDP192 W60 W
Memory32 GB HBM264 GB LPDDR5
Memory bandwidth1,200 GB/s204.8 GB/s
BF16 (dense)275 TFLOPS
INT8 (dense)275 TOPS275 TOPS
Form factorOAM (per-chip in v4 pod)Module (AGX Orin 64GB)
Announced2021-05-182022-03-22
Released2022-05-012022-07-01

Robots running Google TPU v4

No robots publicly running it yet.

Data centers with NVIDIA Jetson AGX Orin

No data centers publicly running it yet.

Common questions

Google TPU v4 vs NVIDIA Jetson AGX Orin: which has more memory?

NVIDIA Jetson AGX Orin carries more HBM (Google TPU v4: 32 GB HBM2; NVIDIA Jetson AGX Orin: 64 GB LPDDR5). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

Google TPU v4 vs NVIDIA Jetson AGX Orin: which is more widely used?

Google TPU v4: 0 robots and 2 data centers publicly running it. NVIDIA Jetson AGX Orin: 9 robots and 0 data centers. Empty here means no operator has said publicly, not zero adoption in the market.

See also: every chip comparison · Google TPU v4 full page · NVIDIA Jetson AGX Orin full page.