Chip comparison
AMD Instinct MI325X vs Huawei Ascend 910B
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 | AMD Instinct MI325X | Huawei Ascend 910B |
|---|---|---|
| Process node | TSMC N5 + N6 (chiplet) | SMIC N+2 (~7nm) |
| TDP | 1000 W | 400 W |
| Memory | 256 GB HBM3e | 64 GB HBM2e |
| Memory bandwidth | 6,000 GB/s | 1,600 GB/s |
| FP16 (dense) | 1,307 TFLOPS | 400 TFLOPS |
| BF16 (dense) | 1,307 TFLOPS | 400 TFLOPS |
| FP8 (dense) | 2,614 TFLOPS | — |
| INT8 (dense) | 2,614 TOPS | 800 TOPS |
| Form factor | OAM | OAM (Atlas 300T A2) |
| Announced | 2024-10-10 | 2023-08-01 |
| Released | 2025-01-01 | 2023-08-01 |
Robots running AMD Instinct MI325X
No robots publicly running it yet.
Robots running Huawei Ascend 910B
Data centers with AMD Instinct MI325X
No data centers publicly running it yet.
Data centers with Huawei Ascend 910B
Common questions
AMD Instinct MI325X vs Huawei Ascend 910B: which is faster for training?
AMD Instinct MI325X has 6.54x the dense FP16/BF16 throughput of the other (AMD Instinct MI325X: 2,614 TFLOPS; Huawei Ascend 910B: 400 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.
AMD Instinct MI325X vs Huawei Ascend 910B: which has more memory?
AMD Instinct MI325X carries more HBM (AMD Instinct MI325X: 256 GB HBM3e; Huawei Ascend 910B: 64 GB HBM2e). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
AMD Instinct MI325X vs Huawei Ascend 910B: which is more power-efficient?
Dense FP16/BF16 TFLOPS per watt: AMD Instinct MI325X 2.61 (2,614 ÷ 1000 W); Huawei Ascend 910B 1.00 (400 ÷ 400 W). AMD Instinct MI325X wins at the die level; system-level efficiency also depends on cooling and interconnect.
AMD Instinct MI325X vs Huawei Ascend 910B: which is more widely used?
AMD Instinct MI325X: 0 robots and 0 data centers publicly running it. Huawei Ascend 910B: 2 robots and 1 data center. Empty here means no operator has said publicly, not zero adoption in the market.
See also: every chip comparison · AMD Instinct MI325X full page · Huawei Ascend 910B full page.