Chip comparison
Google TPU v4 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.
| Field | Google TPU v4 | NVIDIA Jetson AGX Thor |
|---|---|---|
| Process node | TSMC N7 | TSMC 4NP |
| TDP | 192 W | 130 W |
| Memory | 32 GB HBM2 | 128 GB LPDDR5X |
| Memory bandwidth | 1,200 GB/s | 273 GB/s |
| BF16 (dense) | 275 TFLOPS | — |
| FP8 (dense) | — | 2,070 TFLOPS |
| INT8 (dense) | 275 TOPS | 2,070 TOPS |
| Form factor | OAM (per-chip in v4 pod) | Module (AGX Thor) |
| Announced | 2021-05-18 | 2024-03-18 |
| Released | 2022-05-01 | 2025-08-01 |
Robots running Google TPU v4
No robots publicly running it yet.
Data centers with Google TPU v4
Data centers with NVIDIA Jetson AGX Thor
No data centers publicly running it yet.
Common questions
Google TPU v4 vs NVIDIA Jetson AGX Thor: which is faster for training?
NVIDIA Jetson AGX Thor has 7.53x the dense FP16/BF16 throughput of the other (Google TPU v4: 275 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 v4 vs NVIDIA Jetson AGX Thor: which has more memory?
NVIDIA Jetson AGX Thor carries more HBM (Google TPU v4: 32 GB HBM2; 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 v4 vs NVIDIA Jetson AGX Thor: which is more power-efficient?
Dense FP16/BF16 TFLOPS per watt: Google TPU v4 1.43 (275 ÷ 192 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 v4 vs NVIDIA Jetson AGX Thor: which is more widely used?
Google TPU v4: 0 robots and 2 data centers 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 v4 full page · NVIDIA Jetson AGX Thor full page.