Huawei Ascend 910A vs Huawei Ascend 910B

The Ascend 910B delivers 56% more FP16 throughput than the Ascend 910A (400 vs 256 TFLOPS dense). The Ascend 910B also carries 32 GB more memory (64 GB vs 32 GB).

Ascend 910A: Da Vinci, 2019 Ascend 910B: Da Vinci v2, 2024

FP16 dense lead

+56%

Ascend 910B: 400 vs 256 TFLOPS

Memory

32 vs 64 GB

32 GB more for the Ascend 910B

Bandwidth

1.2 TB/s vs 1.6 TB/s

Ascend 910B moves data faster

TDP

310 W vs 400 W

Ascend 910A draws 90 W less

Download comparison sheet Printable version →

Huawei Ascend 910A

Full specs →

What is the Huawei Ascend 910A?

The Ascend 910A is an NPU from Huawei on the Da Vinci architecture, an accelerator built for AI inference. It is an OAM module, the open accelerator format used in multi-GPU servers. Ascend 910A full specifications →

Can I rent the Ascend 910A in the cloud?

Flopper is not tracking any live rental listings for the Ascend 910A yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Ascend 910A compare with other accelerators?

This page sets the Ascend 910A against the Ascend 910B. The Ascend 910A is the older generation of the two. Both are Huawei parts, and both ship as an OAM module, so they fit the same class of system. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the Ascend 910A figures come from?

Every Ascend 910A figure on this page traces to Huawei's own datasheet or specification table. How Flopper verifies specifications →

Huawei Ascend 910B

Leads on FP16 Full specs →

What is the Huawei Ascend 910B?

The Ascend 910B is an NPU from Huawei on the Da Vinci v2 architecture, an accelerator built for AI inference. It is an OAM module, the open accelerator format used in multi-GPU servers. Ascend 910B full specifications →

Can I rent the Ascend 910B in the cloud?

Flopper is not tracking any live rental listings for the Ascend 910B yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Ascend 910B compare with other accelerators?

This page sets the Ascend 910B against the Ascend 910A. The Ascend 910B is the newer generation of the two. Both are Huawei parts, and both ship as an OAM module, so they fit the same class of system. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the Ascend 910B figures come from?

Huawei published the Ascend 910B figures in marketing material rather than a datasheet, and Flopper has no independent confirmation of them. How Flopper verifies specifications →

Specifications

Ascend 910A

Ascend 910B

Architecture

Da VinciDa Vinci v2

Launch Year

20192024

Form Factor

OAMOAM

Memory

32 GB64 GB

Memory Bandwidth

1.2 TB/s1.6 TB/s

TDP

310 W400 W

Process Node

TSMC 7nmSMIC 7nm

Spec

Ascend 910A

Ascend 910B

Architecture Da VinciDa Vinci v2

Launch Year 20192024

Form Factor OAMOAM

Memory 32 GB64 GB

Memory Bandwidth 1.2 TB/s1.6 TB/s

TDP 310 W400 W

Process Node TSMC 7nmSMIC 7nm

Performance (TFLOPS)

Ascend 910A

Ascend 910B

16 TFLOPS

400 TFLOPS

256 TFLOPS 400 TFLOPS

FP6

512 TOPS 800 TOPS

Precision

Ascend 910A

Ascend 910B

16 TFLOPS

400 TFLOPS

256 TFLOPS 400 TFLOPS

FP6

512 TOPS 800 TOPS

Figures are dense. Where a vendor publishes a figure it sits under the dense one and never decides a winner. Hover any precision for its definition, or read the GPU glossary.

FLOPS by Precision

What actually differs

The Ascend 910B is the newer part: Da Vinci v2 (2024) against the Ascend 910A's Da Vinci (2019).

The Ascend 910B carries 32 GB more memory (64 GB against 32 GB), so larger models fit on one GPU before you shard. Bandwidth is 1.2 TB/s against 1.6 TB/s, which sets the ceiling on decode speed.

Power is 310 W against 400 W, and at FP32 the Ascend 910A does more work per watt. Weight the FP8 and FP16 rows for LLM work and the FP64 row for HPC.

New to the terms? The glossary explains FP32, BF16, FP16, INT8, Sparsity and TFLOPS.

Frequently asked questions

What is better, the Ascend 910A or the Ascend 910B?

The Ascend 910B, on throughput. At FP16 precision the Ascend 910B reaches 400 TFLOPS dense against 256 TFLOPS for the Ascend 910A. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the Ascend 910A or the Ascend 910B?

Choose the Ascend 910B for training and high-throughput inference: it has 56% more FP16 throughput than the Ascend 910A. It also carries 32 GB more memory, so larger models fit on one GPU before you shard. The Ascend 910B draws 90 W more power, so budget for cooling and power delivery before you commit.

Which has more memory, the Ascend 910A or the Ascend 910B?

The Ascend 910B carries 64 GB of memory versus 32 GB for the Ascend 910A. Memory bandwidth is 1.2 TB/s for the Ascend 910A and 1.6 TB/s for the Ascend 910B.

How much power do the Ascend 910A and the Ascend 910B draw?

The Ascend 910A is rated at 310 W TDP and the Ascend 910B at 400 W. On FP32 throughput per watt, the Ascend 910A is the more efficient part.

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.

Open in Full Compare Tool → Ascend 910A full specs Ascend 910B full specs Estimate cluster cost in the calculator →

Huawei Ascend 910A vs Huawei Ascend 910B

Huawei Ascend 910A

What is the Huawei Ascend 910A?

Can I rent the Ascend 910A in the cloud?

How does the Ascend 910A compare with other accelerators?

Where do the Ascend 910A figures come from?

Huawei Ascend 910B

What is the Huawei Ascend 910B?

Can I rent the Ascend 910B in the cloud?

How does the Ascend 910B compare with other accelerators?

Where do the Ascend 910B figures come from?

Specifications

Performance (TFLOPS)

FLOPS by Precision

What actually differs

Frequently asked questions

What is better, the Ascend 910A or the Ascend 910B?

Which should you choose, the Ascend 910A or the Ascend 910B?

Which has more memory, the Ascend 910A or the Ascend 910B?

How much power do the Ascend 910A and the Ascend 910B draw?

Get Comparison Updates

Stay Updated on GPU Specs