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	NVIDIA GeForce RTX 5080	AMD MI300A	Etched Sohu
Architecture	Wafer Scale Engine	Blackwell	CDNA 3	Transformer ASIC
Form Factor	—	PCIe	OAM	PCIe
VRAM	44 GB	16 GB	128 GB	144 GB
Memory Bandwidth	—	960 GB/s	5,300 GB/s	4,800 GB/s
TFLOPs (FP32)	—	56.28	122.6	10,000
TFLOPs (FP16)	—	112.6	980.6	—
TFLOPs	—	112.6	980.6	10,000
TFLOPs (FP8)	—	—	—	—
TDP	23000 W	360 W	760 W	700 W
Launch Date	Mar 2024	Jan 2025	Dec 2023	Jun 2024

Efficiency Metrics

Metric	WSE-3	GeForce RTX 5080	MI300A	Sohu
TFLOPs per Watt (FP32-eq)	—	0.16	0.65	14.29
Memory Bandwidth per GB	—	60.0 GB/s	41.4 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 Cerebras WSE-3

NVIDIA GeForce RTX 5080

VRAM

2.75x

Need 2.75x GeForce RTX 5080

AMD MI300A

VRAM

0.34x

MI300A has 2.91x more

Etched Sohu

VRAM

0.31x

Sohu has 3.27x more

To match 1x NVIDIA GeForce RTX 5080

Cerebras WSE-3

VRAM

0.36x

WSE-3 has 2.75x more

AMD MI300A

Compute (FP32-eq)

0.11x

MI300A is 8.71x faster

FP32 Compute

0.46x

MI300A is 2.18x faster

VRAM

0.13x

MI300A has 8.00x more

Memory Bandwidth

0.18x

MI300A has 5.52x more

Etched Sohu

Compute (FP32-eq)

0.01x

Sohu is 177.62x faster

FP32 Compute

0.01x

Sohu is 177.68x faster

VRAM

0.11x

Sohu has 9.00x more

Memory Bandwidth

0.20x

Sohu has 5.00x more

To match 1x AMD MI300A

Cerebras WSE-3

VRAM

2.91x

Need 2.91x WSE-3

NVIDIA GeForce RTX 5080

Compute (FP32-eq)

8.71x

Need 8.71x GeForce RTX 5080

FP32 Compute

2.18x

Need 2.18x GeForce RTX 5080

VRAM

8.00x

Need 8.00x GeForce RTX 5080

Memory Bandwidth

5.52x

Need 5.52x GeForce RTX 5080

Etched Sohu

Compute (FP32-eq)

0.05x

Sohu is 20.40x faster

FP32 Compute

0.01x

Sohu is 81.57x faster

VRAM

0.89x

Sohu has 1.13x more

Memory Bandwidth

1.10x

Need 1.10x Sohu

To match 1x Etched Sohu

Cerebras WSE-3

VRAM

3.27x

Need 3.27x WSE-3

NVIDIA GeForce RTX 5080

Compute (FP32-eq)

177.62x

Need 177.62x GeForce RTX 5080

FP32 Compute

177.68x

Need 177.68x GeForce RTX 5080

VRAM

9.00x

Need 9.00x GeForce RTX 5080

Memory Bandwidth

5.00x

Need 5.00x GeForce RTX 5080

AMD MI300A

Compute (FP32-eq)

20.40x

Need 20.40x MI300A

FP32 Compute

81.57x

Need 81.57x MI300A

VRAM

1.13x

Need 1.13x MI300A

Memory Bandwidth

0.91x

MI300A has 1.10x more

Pricing

Price Type	WSE-3	GeForce RTX 5080	MI300A	Sohu
CAPEX (Street Price)	—	—	—	—
OPEX (per hour)	—	—	—	—
Price per TFLOPs (FP32-eq)	—	—	—	—