Huawei Ascend 910C vs Huawei Ascend 950DT

The Ascend 910C delivers 46% more FP16 throughput than the Ascend 950DT (800 vs 547 TFLOPS dense). The Ascend 950DT counters with 16 GB more memory (144 GB vs 128 GB).

Ascend 910C: Da Vinci v2 (dual-die), 2025 Ascend 950DT: Da Vinci v3, 2026

FP16 dense lead

+46%

Ascend 910C: 800 vs 547 TFLOPS

Memory

128 vs 144 GB

16 GB more for the Ascend 950DT

Bandwidth

3.2 TB/s vs 4.0 TB/s

Ascend 950DT moves data faster

Download comparison sheet Printable version →

Huawei Ascend 910C

Leads on FP16 Full specs →

What is the Huawei Ascend 910C?

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

Can I rent the Ascend 910C in the cloud?

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

How does the Ascend 910C compare with other accelerators?

This page sets the Ascend 910C against the Ascend 950DT. The Ascend 910C 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 910C figures come from?

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

Huawei Ascend 950DT

Full specs →

What is the Huawei Ascend 950DT?

The Ascend 950DT is an NPU from Huawei on the Da Vinci v3 architecture, an accelerator built for AI inference. It is an OAM module, the open accelerator format used in multi-GPU servers. Ascend 950DT full specifications →

Can I rent the Ascend 950DT in the cloud?

Flopper is not tracking any live rental listings for the Ascend 950DT yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Ascend 950DT compare with other accelerators?

This page sets the Ascend 950DT against the Ascend 910C. The Ascend 950DT 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 950DT figures come from?

Every Ascend 950DT figure on this page traces to Huawei's own datasheet or specification table. How Flopper verifies specifications →

Specifications

Ascend 910C

Ascend 950DT

Architecture

Da Vinci v2 (dual-die)Da Vinci v3

Launch Year

20252026

Form Factor

OAMOAM

Memory

128 GB144 GB

Memory Bandwidth

3.2 TB/s4.0 TB/s

TDP

600 W—

Process Node

SMIC 7nm—

Spec

Ascend 910C

Ascend 950DT

Architecture Da Vinci v2 (dual-die)Da Vinci v3

Launch Year 20252026

Form Factor OAMOAM

Memory 128 GB144 GB

Memory Bandwidth 3.2 TB/s4.0 TB/s

TDP 600 W—

Process Node SMIC 7nm—

Performance (TFLOPS)

Ascend 910C

Ascend 950DT

50 TFLOPS 30 TFLOPS

273 TFLOPS

800 TFLOPS 547 TFLOPS

1,034 TFLOPS

FP6

2,007 TFLOPS

1,600 TOPS 1,034 TOPS

Precision

Ascend 910C

Ascend 950DT

50 TFLOPS 30 TFLOPS

273 TFLOPS

800 TFLOPS 547 TFLOPS

1,034 TFLOPS

FP6

2,007 TFLOPS

1,600 TOPS 1,034 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 950DT is the newer part: Da Vinci v3 (2026) against the Ascend 910C's Da Vinci v2 (dual-die) (2025).

The Ascend 950DT carries 16 GB more memory (144 GB against 128 GB), so larger models fit on one GPU before you shard. Bandwidth is 3.2 TB/s against 4.0 TB/s, which sets the ceiling on decode speed.

Weight the FP8 and FP16 rows for LLM work and the FP64 row for HPC.

New to the terms? The glossary explains FP32, TF32, BF16, FP16, FP8, FP4, INT8, Sparsity and TFLOPS.

Frequently asked questions

What is better, the Ascend 910C or the Ascend 950DT?

The Ascend 910C, on throughput. At FP16 precision the Ascend 910C reaches 800 TFLOPS dense against 547 TFLOPS for the Ascend 950DT. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the Ascend 910C or the Ascend 950DT?

Choose the Ascend 910C for training and high-throughput inference: it has 46% more FP16 throughput than the Ascend 950DT. Choose the Ascend 950DT when the model has to fit on one GPU: it carries 16 GB more memory.

Which has more memory, the Ascend 910C or the Ascend 950DT?

The Ascend 950DT carries 144 GB of memory versus 128 GB for the Ascend 910C. Memory bandwidth is 3.2 TB/s for the Ascend 910C and 4.0 TB/s for the Ascend 950DT.

Get Comparison Updates

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

Open in Full Compare Tool → Ascend 910C full specs Ascend 950DT full specs Estimate cluster cost in the calculator →

Huawei Ascend 910C vs Huawei Ascend 950DT

Huawei Ascend 910C

What is the Huawei Ascend 910C?

Can I rent the Ascend 910C in the cloud?

How does the Ascend 910C compare with other accelerators?

Where do the Ascend 910C figures come from?

Huawei Ascend 950DT

What is the Huawei Ascend 950DT?

Can I rent the Ascend 950DT in the cloud?

How does the Ascend 950DT compare with other accelerators?

Where do the Ascend 950DT figures come from?

Specifications

Performance (TFLOPS)

FLOPS by Precision

What actually differs

Frequently asked questions

What is better, the Ascend 910C or the Ascend 950DT?

Which should you choose, the Ascend 910C or the Ascend 950DT?

Which has more memory, the Ascend 910C or the Ascend 950DT?

Get Comparison Updates

Stay Updated on GPU Specs