Chip comparison
Huawei Ascend 910B 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 | Huawei Ascend 910B | NVIDIA Jetson AGX Orin |
|---|---|---|
| Process node | SMIC N+2 (~7nm) | Samsung 8N |
| TDP | 400 W | 60 W |
| Memory | 64 GB HBM2e | 64 GB LPDDR5 |
| Memory bandwidth | 1,600 GB/s | 204.8 GB/s |
| FP16 (dense) | 400 TFLOPS | — |
| BF16 (dense) | 400 TFLOPS | — |
| INT8 (dense) | 800 TOPS | 275 TOPS |
| Form factor | OAM (Atlas 300T A2) | Module (AGX Orin 64GB) |
| Announced | 2023-08-01 | 2022-03-22 |
| Released | 2023-08-01 | 2022-07-01 |
Robots running Huawei Ascend 910B
Robots running NVIDIA Jetson AGX Orin
Data centers with Huawei Ascend 910B
Data centers with NVIDIA Jetson AGX Orin
No data centers publicly running it yet.
Common questions
Huawei Ascend 910B vs NVIDIA Jetson AGX Orin: which has more memory?
NVIDIA Jetson AGX Orin carries more HBM (Huawei Ascend 910B: 64 GB HBM2e; 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.
Huawei Ascend 910B vs NVIDIA Jetson AGX Orin: which is more widely used?
Huawei Ascend 910B: 2 robots and 1 data center 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 · Huawei Ascend 910B full page · NVIDIA Jetson AGX Orin full page.