Chip comparison
Huawei Ascend 910B vs NVIDIA L40S
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 L40S |
|---|---|---|
| Process node | SMIC N+2 (~7nm) | TSMC 4N |
| Transistors (B) | — | 76.3 |
| TDP | 400 W | 350 W |
| Memory | 64 GB HBM2e | 48 GB GDDR6 |
| Memory bandwidth | 1,600 GB/s | 864 GB/s |
| FP16 (dense) | 400 TFLOPS | 362 TFLOPS |
| BF16 (dense) | 400 TFLOPS | 362 TFLOPS |
| FP8 (dense) | — | 733 TFLOPS |
| INT8 (dense) | 800 TOPS | 733 TOPS |
| Form factor | OAM (Atlas 300T A2) | PCIe |
| Announced | 2023-08-01 | 2023-08-08 |
| Released | 2023-08-01 | — |
Robots running Huawei Ascend 910B
Robots running NVIDIA L40S
No robots publicly running it yet.
Data centers with Huawei Ascend 910B
Data centers with NVIDIA L40S
No data centers publicly running it yet.
Common questions
Huawei Ascend 910B vs NVIDIA L40S: which is faster for training?
NVIDIA L40S has 1.83x the dense FP16/BF16 throughput of the other (Huawei Ascend 910B: 400 TFLOPS; NVIDIA L40S: 733 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.
Huawei Ascend 910B vs NVIDIA L40S: which has more memory?
Huawei Ascend 910B carries more HBM (Huawei Ascend 910B: 64 GB HBM2e; NVIDIA L40S: 48 GB GDDR6). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
Huawei Ascend 910B vs NVIDIA L40S: which is more power-efficient?
Dense FP16/BF16 TFLOPS per watt: Huawei Ascend 910B 1.00 (400 ÷ 400 W); NVIDIA L40S 2.09 (733 ÷ 350 W). NVIDIA L40S wins at the die level; system-level efficiency also depends on cooling and interconnect.
Huawei Ascend 910B vs NVIDIA L40S: which is more widely used?
Huawei Ascend 910B: 2 robots and 1 data center publicly running it. NVIDIA L40S: 0 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 L40S full page.