Layer 2 · head to head
Huawei Ascend 910C vs NVIDIA H100
A jurisdiction comparison, not a performance one.
| Huawei Ascend 910C | NVIDIA H100 | |
|---|---|---|
| Can you get it | Export controls or regional restrictions govern access. | Rentable by the hour from multiple clouds; purchasable at scale. |
| Memory | Not reliably published outside China | 80 GB HBM3 |
| Bandwidth | Not reliably published | 3.35 TB/s |
| Compute | Positioned against H100-class parts | Hopper-generation FP8 |
| Power | Not published | 700 W |
| Interconnect | HCCS | NVLink 4 |
| Software | CANN, MindSpore | CUDA |
| Workload | both | both |
Huawei Ascend 910C
For: Buyers inside China, where export controls make the NVIDIA question moot.
The catch: Export controls cut both ways: availability outside China is effectively nil, and independent Western benchmarks are scarce enough that every published figure should be treated as a vendor claim.
Economics: Not a price comparison. It is a jurisdiction decision.
NVIDIA H100
For: The reference point everything else is benchmarked against, and still the most rentable accelerator on earth.
The catch: 80 GB is the binding limit. Large models need multi-GPU sharding that a 141 GB or 288 GB part would not, and sharding costs you latency and complexity.
Economics: The benchmark denominator. When a vendor claims '2.6x an H100', this is the H100 they mean.
Before either — can you power it?
Not published against 700 W. In 2026 that comparison usually matters more than the FLOPS one: the US interconnection queue exceeds 2,600 GW with waits approaching five years, and roughly 80% of projects withdraw before energising.