DEPLOYDatabase

Chip comparison

Google TPU v6 (Trillium) vs NVIDIA Jetson AGX Thor

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 v6 (Trillium)NVIDIA Jetson AGX Thor
Process nodeTSMC 4NP
TDP200 W130 W
Memory32 GB HBM3128 GB LPDDR5X
Memory bandwidth1,600 GB/s273 GB/s
BF16 (dense)918 TFLOPS
FP8 (dense)1,836 TFLOPS2,070 TFLOPS
INT8 (dense)1,836 TOPS2,070 TOPS
Form factorOAM (Trillium pod, up to 256 chips)Module (AGX Thor)
Announced2024-05-142024-03-18
Released2024-12-012025-08-01

Robots running Google TPU v6 (Trillium)

No robots publicly running it yet.

Robots running NVIDIA Jetson AGX Thor

Data centers with Google TPU v6 (Trillium)

Data centers with NVIDIA Jetson AGX Thor

No data centers publicly running it yet.

Common questions

Google TPU v6 (Trillium) vs NVIDIA Jetson AGX Thor: which is faster for training?

NVIDIA Jetson AGX Thor has 1.13x the dense FP8 throughput of the other (Google TPU v6 (Trillium): 1,836 TFLOPS; NVIDIA Jetson AGX Thor: 2,070 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

Google TPU v6 (Trillium) vs NVIDIA Jetson AGX Thor: which has more memory?

NVIDIA Jetson AGX Thor carries more HBM (Google TPU v6 (Trillium): 32 GB HBM3; NVIDIA Jetson AGX Thor: 128 GB LPDDR5X). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

Google TPU v6 (Trillium) vs NVIDIA Jetson AGX Thor: which is more power-efficient?

Dense FP8 TFLOPS per watt: Google TPU v6 (Trillium) 9.18 (1,836 ÷ 200 W); NVIDIA Jetson AGX Thor 15.92 (2,070 ÷ 130 W). NVIDIA Jetson AGX Thor wins at the die level; system-level efficiency also depends on cooling and interconnect.

Google TPU v6 (Trillium) vs NVIDIA Jetson AGX Thor: which is more widely used?

Google TPU v6 (Trillium): 0 robots and 1 data center publicly running it. NVIDIA Jetson AGX Thor: 11 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 v6 (Trillium) full page · NVIDIA Jetson AGX Thor full page.