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	Cerebras WSE-3	Tenstorrent Wormhole	NVIDIA GB200 NVL72	Google TPU v6e (Trillium)
Architecture	Wafer Scale Engine	Tensix Core	Blackwell	Trillium
Form Factor	—	—	Custom	Custom
VRAM	44 GB	24 GB	13824 GB	32 GB
Memory Bandwidth	—	—	130,000 GB/s	1,600 GB/s
TFLOPs (FP32)	—	—	6,480	459
TFLOPs (FP16)	—	—	360,000	918
TFLOPs	—	364	360,000	918
TFLOPs (FP8)	—	—	—	—
TDP	23000 W	160 W	120000 W	200 W
Launch Date	Mar 2024	Oct 2023	Mar 2024	May 2024

Efficiency Metrics

Metric	WSE-3	Wormhole	GB200 NVL72	TPU v6e (Trillium)
TFLOPs per Watt (FP32-eq)	—	1.14	1.50	2.29
Memory Bandwidth per GB	—	—	9.4 GB/s	50.0 GB/s

Performance Equivalence

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

To match 1x Cerebras WSE-3

Tenstorrent Wormhole

VRAM

1.83x

Need 1.83x Wormhole

NVIDIA GB200 NVL72

VRAM

0.00x

GB200 NVL72 has 314.18x more

Google TPU v6e (Trillium)

VRAM

1.38x

Need 1.38x TPU v6e (Trillium)

To match 1x Tenstorrent Wormhole

Cerebras WSE-3

VRAM

0.55x

WSE-3 has 1.83x more

NVIDIA GB200 NVL72

Compute (FP32-eq)

0.00x

GB200 NVL72 is 989.01x faster

VRAM

0.00x

GB200 NVL72 has 576.00x more

Google TPU v6e (Trillium)

Compute (FP32-eq)

0.40x

TPU v6e (Trillium) is 2.52x faster

VRAM

0.75x

TPU v6e (Trillium) has 1.33x more

To match 1x NVIDIA GB200 NVL72

Cerebras WSE-3

VRAM

314.18x

Need 314.18x WSE-3

Tenstorrent Wormhole

Compute (FP32-eq)

989.01x

Need 989.01x Wormhole

VRAM

576.00x

Need 576.00x Wormhole

Google TPU v6e (Trillium)

Compute (FP32-eq)

392.16x

Need 392.16x TPU v6e (Trillium)

FP32 Compute

14.12x

Need 14.12x TPU v6e (Trillium)

VRAM

432.00x

Need 432.00x TPU v6e (Trillium)

Memory Bandwidth

81.25x

Need 81.25x TPU v6e (Trillium)

To match 1x Google TPU v6e (Trillium)

Cerebras WSE-3

VRAM

0.73x

WSE-3 has 1.38x more

Tenstorrent Wormhole

Compute (FP32-eq)

2.52x

Need 2.52x Wormhole

VRAM

1.33x

Need 1.33x Wormhole

NVIDIA GB200 NVL72

Compute (FP32-eq)

0.00x

GB200 NVL72 is 392.16x faster

FP32 Compute

0.07x

GB200 NVL72 is 14.12x faster

VRAM

0.00x

GB200 NVL72 has 432.00x more

Memory Bandwidth

0.01x

GB200 NVL72 has 81.25x more

Pricing

Price Type	WSE-3	Wormhole	GB200 NVL72	TPU v6e (Trillium)
CAPEX (Street Price)	—	—	—	—
OPEX (per hour)	—	—	—	—
Price per TFLOPs (FP32-eq)	—	—	—	—