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 A40	Tenstorrent Grayskull	AWS Inferentia2	Etched Sohu
Architecture	Ampere	Tensix Core	Inferentia Gen2	Transformer ASIC
Form Factor	PCIe	—	—	PCIe
VRAM	48 GB	8 GB	32 GB	144 GB
Memory Bandwidth	696 GB/s	—	—	4,800 GB/s
TFLOPs (FP32)	37.4	—	—	10,000
TFLOPs (FP16)	150	—	—	—
TFLOPs	150	200	190	10,000
TFLOPs (FP8)	—	—	—	—
TDP	300 W	65 W	150 W	700 W
Launch Date	Oct 2020	Mar 2021	Nov 2022	Jun 2024

Efficiency Metrics

Metric	A40	Grayskull	Inferentia2	Sohu
TFLOPs per Watt (FP32-eq)	0.25	1.54	0.63	14.29
Memory Bandwidth per GB	14.5 GB/s	—	—	33.3 GB/s

Performance Equivalence

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

To match 1x NVIDIA A40

Tenstorrent Grayskull

Compute (FP32-eq)

0.75x

Grayskull is 1.33x faster

VRAM

6.00x

Need 6.00x Grayskull

AWS Inferentia2

Compute (FP32-eq)

0.79x

Inferentia2 is 1.27x faster

VRAM

1.50x

Need 1.50x Inferentia2

Etched Sohu

Compute (FP32-eq)

0.01x

Sohu is 133.33x faster

FP32 Compute

0.00x

Sohu is 267.38x faster

VRAM

0.33x

Sohu has 3.00x more

Memory Bandwidth

0.14x

Sohu has 6.90x more

To match 1x Tenstorrent Grayskull

NVIDIA A40

Compute (FP32-eq)

1.33x

Need 1.33x A40

VRAM

0.17x

A40 has 6.00x more

AWS Inferentia2

Compute (FP32-eq)

1.05x

Need 1.05x Inferentia2

VRAM

0.25x

Inferentia2 has 4.00x more

Etched Sohu

Compute (FP32-eq)

0.01x

Sohu is 100.00x faster

VRAM

0.06x

Sohu has 18.00x more

To match 1x AWS Inferentia2

NVIDIA A40

Compute (FP32-eq)

1.27x

Need 1.27x A40

VRAM

0.67x

A40 has 1.50x more

Tenstorrent Grayskull

Compute (FP32-eq)

0.95x

Grayskull is 1.05x faster

VRAM

4.00x

Need 4.00x Grayskull

Etched Sohu

Compute (FP32-eq)

0.01x

Sohu is 105.26x faster

VRAM

0.22x

Sohu has 4.50x more

To match 1x Etched Sohu

NVIDIA A40

Compute (FP32-eq)

133.33x

Need 133.33x A40

FP32 Compute

267.38x

Need 267.38x A40

VRAM

3.00x

Need 3.00x A40

Memory Bandwidth

6.90x

Need 6.90x A40

Tenstorrent Grayskull

Compute (FP32-eq)

100.00x

Need 100.00x Grayskull

VRAM

18.00x

Need 18.00x Grayskull

AWS Inferentia2

Compute (FP32-eq)

105.26x

Need 105.26x Inferentia2

VRAM

4.50x

Need 4.50x Inferentia2

Pricing

Price Type	A40	Grayskull	Inferentia2	Sohu
CAPEX (Street Price)	—	—	—	—
OPEX (per hour)	—	—	—	—
Price per TFLOPs (FP32-eq)	—	—	—	—