Compare XPUs

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

Select XPUs to Compare

Clear all (3)Jump to results

Filter by Vendor

Showing 72 XPUs • 3 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 A100 SXM	Cambricon MLU370	NVIDIA GeForce RTX 4070 Ti Super
Architecture	Ampere	MLU Core	Ada Lovelace
Form Factor	SXM	—	PCIe
VRAM	80 GB	48 GB	16 GB
Memory Bandwidth	2,039 GB/s	—	672 GB/s
TFLOPs (FP32)	19.5	—	44.1
TFLOPs (FP16)	312	—	88.2
TFLOPs	312	256	88.2
TFLOPs (FP8)	—	—	—
TDP	400 W	300 W	285 W
Launch Date	May 2020	Nov 2022	Jan 2024

Efficiency Metrics

Metric	A100 SXM	MLU370	GeForce RTX 4070 Ti Super
TFLOPs per Watt (FP32-eq)	0.39	0.43	0.15
Memory Bandwidth per GB	25.5 GB/s	—	42.0 GB/s

Performance Equivalence

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

To match 1x NVIDIA A100 SXM

Cambricon MLU370

Compute (FP32-eq)

1.22x

Need 1.22x MLU370

VRAM

1.67x

Need 1.67x MLU370

NVIDIA GeForce RTX 4070 Ti Super

Compute (FP32-eq)

3.54x

Need 3.54x GeForce RTX 4070 Ti Super

FP32 Compute

0.44x

GeForce RTX 4070 Ti Super is 2.26x faster

VRAM

5.00x

Need 5.00x GeForce RTX 4070 Ti Super

Memory Bandwidth

3.03x

Need 3.03x GeForce RTX 4070 Ti Super

To match 1x Cambricon MLU370

NVIDIA A100 SXM

Compute (FP32-eq)

0.82x

A100 SXM is 1.22x faster

VRAM

0.60x

A100 SXM has 1.67x more

NVIDIA GeForce RTX 4070 Ti Super

Compute (FP32-eq)

2.90x

Need 2.90x GeForce RTX 4070 Ti Super

VRAM

3.00x

Need 3.00x GeForce RTX 4070 Ti Super

To match 1x NVIDIA GeForce RTX 4070 Ti Super

NVIDIA A100 SXM

Compute (FP32-eq)

0.28x

A100 SXM is 3.54x faster

FP32 Compute

2.26x

Need 2.26x A100 SXM

VRAM

0.20x

A100 SXM has 5.00x more

Memory Bandwidth

0.33x

A100 SXM has 3.03x more

Cambricon MLU370

Compute (FP32-eq)

0.34x

MLU370 is 2.90x faster

VRAM

0.33x

MLU370 has 3.00x more

Pricing

Price Type	A100 SXM	MLU370	GeForce RTX 4070 Ti Super
CAPEX (Street Price)	$15,000	—	—
OPEX (per hour)	$4.05/hr	—	—
Price per TFLOPs (FP32-eq)	$96	—	—