Compare XPUs

Select up to 5 XPUs to compare side-by-side

Select XPUs to Compare

Clear all (4)Jump to results

Filter by Vendor

Showing 72 XPUs • 4 selected

Alibaba

Hanguang 800

AMD

MI100

23.1 TFLOPs

AMD

MI210

181 TFLOPs

AMD

MI250X

383 TFLOPs

AMD

MI300A

980.6 TFLOPs

AMD

MI300X

1,307 TFLOPs

AMD

MI325X

1,400 TFLOPs

AMD

MI350X

2,100 TFLOPs

AMD

Radeon PRO W7900

122 TFLOPs

AMD

Radeon RX 7900 XT

104 TFLOPs

AMD

Radeon RX 7900 XTX

122 TFLOPs

AWS

Inferentia2

190 TFLOPs

AWS

Trainium

190 TFLOPs

AWS

Trainium2

680 TFLOPs

Baidu

Kunlun II

Biren Technology

BR100

Cambricon

MLU370

256 TFLOPs

Cerebras

WSE-3

Enflame Technology

CloudBlazer T20

Etched

Sohu

10,000 TFLOPs

FuriosaAI

Warboy

Google

TPU v4

275 TFLOPs

Google

TPU v5e

197 TFLOPs

Google

TPU v5p

459 TFLOPs

Google

TPU v6e (Trillium)

918 TFLOPs

Graphcore

Bow IPU

Graphcore

IPU-M2000

Groq

LPU Inference Engine

Huawei

Ascend 910B

Iluvatar CoreX

BI-V150

300 TFLOPs

Intel

Data Center GPU Max 1100

177 TFLOPs

Intel

Data Center GPU Max 1550

419 TFLOPs

Intel Habana

Gaudi 2

432 TFLOPs

Intel Habana

Gaudi 3

1,835 TFLOPs

Multi-Metric Comparison

Relative performance across 5 key metrics (normalized to 100 = best in comparison)

Compute Performance (BF16)

Memory Capacity

Power Consumption

Power Efficiency

Specifications

Specification	NVIDIA A10	Qualcomm Cloud AI 100	Huawei Ascend 910B	Baidu Kunlun II
Architecture	Ampere	Qualcomm AI	Da Vinci	Kunlun Core
Form Factor	PCIe	PCIe	—	—
VRAM	24 GB	16 GB	64 GB	32 GB
Memory Bandwidth	600 GB/s	134 GB/s	—	—
TFLOPs (FP32)	31.2	50	—	—
TFLOPs (FP16)	125	400	640	256
TFLOPs	125	50	—	—
TFLOPs (FP8)	—	—	—	—
TDP	150 W	75 W	400 W	200 W
Launch Date	Apr 2021	Sep 2020	Aug 2023	Aug 2021

Efficiency Metrics

Metric	A10	Cloud AI 100	Ascend 910B	Kunlun II
TFLOPs per Watt (FP32-eq)	0.42	0.67	—	—
Memory Bandwidth per GB	25.0 GB/s	8.4 GB/s	—	—

Performance Equivalence

How many units of each GPU are needed to match the performance of the others?

To match 1x NVIDIA A10

Qualcomm Cloud AI 100

Compute (FP32-eq)

1.25x

Need 1.25x Cloud AI 100

FP32 Compute

0.62x

Cloud AI 100 is 1.60x faster

VRAM

1.50x

Need 1.50x Cloud AI 100

Memory Bandwidth

4.48x

Need 4.48x Cloud AI 100

Huawei Ascend 910B

VRAM

0.38x

Ascend 910B has 2.67x more

Baidu Kunlun II

VRAM

0.75x

Kunlun II has 1.33x more

To match 1x Qualcomm Cloud AI 100

NVIDIA A10

Compute (FP32-eq)

0.80x

A10 is 1.25x faster

FP32 Compute

1.60x

Need 1.60x A10

VRAM

0.67x

A10 has 1.50x more

Memory Bandwidth

0.22x

A10 has 4.48x more

Huawei Ascend 910B

VRAM

0.25x

Ascend 910B has 4.00x more

Baidu Kunlun II

VRAM

0.50x

Kunlun II has 2.00x more

To match 1x Huawei Ascend 910B

NVIDIA A10

VRAM

2.67x

Need 2.67x A10

Qualcomm Cloud AI 100

VRAM

4.00x

Need 4.00x Cloud AI 100

Baidu Kunlun II

VRAM

2.00x

Need 2.00x Kunlun II

To match 1x Baidu Kunlun II

NVIDIA A10

VRAM

1.33x

Need 1.33x A10

Qualcomm Cloud AI 100

VRAM

2.00x

Need 2.00x Cloud AI 100

Huawei Ascend 910B

VRAM

0.50x

Ascend 910B has 2.00x more

Pricing

Price Type	A10	Cloud AI 100	Ascend 910B	Kunlun II
CAPEX (Street Price)	—	—	—	—
OPEX (per hour)	—	—	—	—
Price per TFLOPs (FP32-eq)	—	—	—	—