Chip comparison
NVIDIA GB200 Grace Blackwell Superchip 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.
| Field | NVIDIA GB200 Grace Blackwell Superchip | NVIDIA Jetson AGX Orin |
|---|---|---|
| Process node | TSMC 4NP | Samsung 8N |
| TDP | 2700 W | 60 W |
| Memory | 384 GB HBM3e | 64 GB LPDDR5 |
| Memory bandwidth | 16,000 GB/s | 204.8 GB/s |
| FP8 (dense) | 9,000 TFLOPS | — |
| INT8 (dense) | — | 275 TOPS |
| Form factor | Superchip (2xB200 + 1xGrace) | Module (AGX Orin 64GB) |
| Announced | 2024-03-18 | 2022-03-22 |
| Released | 2024-12-01 | 2022-07-01 |
Robots running NVIDIA GB200 Grace Blackwell Superchip
No robots publicly running it yet.
Robots running NVIDIA Jetson AGX Orin
Data centers with NVIDIA GB200 Grace Blackwell Superchip
Data centers with NVIDIA Jetson AGX Orin
No data centers publicly running it yet.
Common questions
NVIDIA GB200 Grace Blackwell Superchip vs NVIDIA Jetson AGX Orin: which has more memory?
NVIDIA GB200 Grace Blackwell Superchip carries more HBM (NVIDIA GB200 Grace Blackwell Superchip: 384 GB HBM3e; 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.
NVIDIA GB200 Grace Blackwell Superchip vs NVIDIA Jetson AGX Orin: which is more widely used?
NVIDIA GB200 Grace Blackwell Superchip: 0 robots and 11 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 · NVIDIA GB200 Grace Blackwell Superchip full page · NVIDIA Jetson AGX Orin full page.