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 B200	Cerebras WSE-3	NVIDIA H100 PCIe	AMD MI300A
Architecture	Blackwell	Wafer Scale Engine	Hopper	CDNA 3
Form Factor	SXM	—	PCIe	OAM
VRAM	192 GB	44 GB	80 GB	128 GB
Memory Bandwidth	8,000 GB/s	—	2,000 GB/s	5,300 GB/s
TFLOPs (FP32)	90	—	51	122.6
TFLOPs (FP16)	2,250	—	1,513	980.6
TFLOPs	2,250	—	1,513	980.6
TFLOPs (FP8)	4,500	—	—	—
TDP	1000 W	23000 W	350 W	760 W
Launch Date	Mar 2024	Mar 2024	Sep 2022	Dec 2023

Efficiency Metrics

Metric	B200	WSE-3	H100 PCIe	MI300A
TFLOPs per Watt (FP32-eq)	1.13	—	2.16	0.65
Memory Bandwidth per GB	41.7 GB/s	—	25.0 GB/s	41.4 GB/s

Performance Equivalence

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

To match 1x NVIDIA B200

Cerebras WSE-3

VRAM

4.36x

Need 4.36x WSE-3

NVIDIA H100 PCIe

Compute (FP32-eq)

1.49x

Need 1.49x H100 PCIe

FP32 Compute

1.76x

Need 1.76x H100 PCIe

VRAM

2.40x

Need 2.40x H100 PCIe

Memory Bandwidth

4.00x

Need 4.00x H100 PCIe

AMD MI300A

Compute (FP32-eq)

2.29x

Need 2.29x MI300A

FP32 Compute

0.73x

MI300A is 1.36x faster

VRAM

1.50x

Need 1.50x MI300A

Memory Bandwidth

1.51x

Need 1.51x MI300A

To match 1x Cerebras WSE-3

NVIDIA B200

VRAM

0.23x

B200 has 4.36x more

NVIDIA H100 PCIe

VRAM

0.55x

H100 PCIe has 1.82x more

AMD MI300A

VRAM

0.34x

MI300A has 2.91x more

To match 1x NVIDIA H100 PCIe

NVIDIA B200

Compute (FP32-eq)

0.67x

B200 is 1.49x faster

FP32 Compute

0.57x

B200 is 1.76x faster

VRAM

0.42x

B200 has 2.40x more

Memory Bandwidth

0.25x

B200 has 4.00x more

Cerebras WSE-3

VRAM

1.82x

Need 1.82x WSE-3

AMD MI300A

Compute (FP32-eq)

1.54x

Need 1.54x MI300A

FP32 Compute

0.42x

MI300A is 2.40x faster

VRAM

0.63x

MI300A has 1.60x more

Memory Bandwidth

0.38x

MI300A has 2.65x more

To match 1x AMD MI300A

NVIDIA B200

Compute (FP32-eq)

0.44x

B200 is 2.29x faster

FP32 Compute

1.36x

Need 1.36x B200

VRAM

0.67x

B200 has 1.50x more

Memory Bandwidth

0.66x

B200 has 1.51x more

Cerebras WSE-3

VRAM

2.91x

Need 2.91x WSE-3

NVIDIA H100 PCIe

Compute (FP32-eq)

0.65x

H100 PCIe is 1.54x faster

FP32 Compute

2.40x

Need 2.40x H100 PCIe

VRAM

1.60x

Need 1.60x H100 PCIe

Memory Bandwidth

2.65x

Need 2.65x H100 PCIe

Pricing

Price Type	B200	WSE-3	H100 PCIe	MI300A
CAPEX (Street Price)	$70,000	—	—	—
OPEX (per hour)	—	—	—	—
Price per TFLOPs (FP32-eq)	$62	—	—	—