DEPLOYDatabase

Chip comparison

Huawei Ascend 910B vs NVIDIA T4 Tensor Core GPU

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.

FieldHuawei Ascend 910BNVIDIA T4 Tensor Core GPU
Process nodeSMIC N+2 (~7nm)TSMC 12FFN
Transistors (B)13.6
Die size545 mm²
TDP400 W70 W
Memory64 GB HBM2e16 GB GDDR6
Memory bandwidth1,600 GB/s320 GB/s
FP16 (dense)400 TFLOPS65 TFLOPS
BF16 (dense)400 TFLOPS
INT8 (dense)800 TOPS130 TOPS
Form factorOAM (Atlas 300T A2)PCIe (single-slot, low-profile)
Announced2023-08-012018-09-13
Released2023-08-012019-01-01

Robots running Huawei Ascend 910B

Robots running NVIDIA T4 Tensor Core GPU

No robots publicly running it yet.

Data centers with Huawei Ascend 910B

Data centers with NVIDIA T4 Tensor Core GPU

No data centers publicly running it yet.

Common questions

Huawei Ascend 910B vs NVIDIA T4 Tensor Core GPU: which is faster for training?

Huawei Ascend 910B has 6.15x the dense FP16/BF16 throughput of the other (Huawei Ascend 910B: 400 TFLOPS; NVIDIA T4 Tensor Core GPU: 65 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 T4 Tensor Core GPU: which has more memory?

Huawei Ascend 910B carries more HBM (Huawei Ascend 910B: 64 GB HBM2e; NVIDIA T4 Tensor Core GPU: 16 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 T4 Tensor Core GPU: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Huawei Ascend 910B 1.00 (400 ÷ 400 W); NVIDIA T4 Tensor Core GPU 0.93 (65 ÷ 70 W). Huawei Ascend 910B wins at the die level; system-level efficiency also depends on cooling and interconnect.

Huawei Ascend 910B vs NVIDIA T4 Tensor Core GPU: which is more widely used?

Huawei Ascend 910B: 2 robots and 1 data center publicly running it. NVIDIA T4 Tensor Core GPU: 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 T4 Tensor Core GPU full page.