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 H200 SXM	AMD MI210	Google TPU v4	AMD Radeon PRO W7900
Architecture	Hopper	CDNA 2	TPU v4	RDNA 3
Form Factor	SXM	PCIe	Mezzanine	PCIe
VRAM	141 GB	64 GB	—	48 GB
Memory Bandwidth	4,800 GB/s	1,638 GB/s	—	864 GB/s
TFLOPs (FP32)	67	45.3	—	61
TFLOPs (FP16)	1,979	181	—	122
TFLOPs	1,979	181	275	122
TFLOPs (FP8)	3,958	—	—	—
TDP	700 W	300 W	300 W	295 W
Launch Date	Nov 2023	Jan 2022	May 2021	Apr 2023

Efficiency Metrics

Metric	H200 SXM	MI210	TPU v4	Radeon PRO W7900
TFLOPs per Watt (FP32-eq)	1.41	0.30	0.46	0.21
Memory Bandwidth per GB	34.0 GB/s	25.6 GB/s	—	18.0 GB/s

Performance Equivalence

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

To match 1x NVIDIA H200 SXM

AMD MI210

Compute (FP32-eq)

10.93x

Need 10.93x MI210

FP32 Compute

1.48x

Need 1.48x MI210

VRAM

2.20x

Need 2.20x MI210

Memory Bandwidth

2.93x

Need 2.93x MI210

Google TPU v4

Compute (FP32-eq)

7.20x

Need 7.20x TPU v4

AMD Radeon PRO W7900

Compute (FP32-eq)

16.22x

Need 16.22x Radeon PRO W7900

FP32 Compute

1.10x

Need 1.10x Radeon PRO W7900

VRAM

2.94x

Need 2.94x Radeon PRO W7900

Memory Bandwidth

5.56x

Need 5.56x Radeon PRO W7900

To match 1x AMD MI210

NVIDIA H200 SXM

Compute (FP32-eq)

0.09x

H200 SXM is 10.93x faster

FP32 Compute

0.68x

H200 SXM is 1.48x faster

VRAM

0.45x

H200 SXM has 2.20x more

Memory Bandwidth

0.34x

H200 SXM has 2.93x more

Google TPU v4

Compute (FP32-eq)

0.66x

TPU v4 is 1.52x faster

AMD Radeon PRO W7900

Compute (FP32-eq)

1.48x

Need 1.48x Radeon PRO W7900

FP32 Compute

0.74x

Radeon PRO W7900 is 1.35x faster

VRAM

1.33x

Need 1.33x Radeon PRO W7900

Memory Bandwidth

1.90x

Need 1.90x Radeon PRO W7900

To match 1x Google TPU v4

NVIDIA H200 SXM

Compute (FP32-eq)

0.14x

H200 SXM is 7.20x faster

AMD MI210

Compute (FP32-eq)

1.52x

Need 1.52x MI210

AMD Radeon PRO W7900

Compute (FP32-eq)

2.25x

Need 2.25x Radeon PRO W7900

To match 1x AMD Radeon PRO W7900

NVIDIA H200 SXM

Compute (FP32-eq)

0.06x

H200 SXM is 16.22x faster

FP32 Compute

0.91x

H200 SXM is 1.10x faster

VRAM

0.34x

H200 SXM has 2.94x more

Memory Bandwidth

0.18x

H200 SXM has 5.56x more

AMD MI210

Compute (FP32-eq)

0.67x

MI210 is 1.48x faster

FP32 Compute

1.35x

Need 1.35x MI210

VRAM

0.75x

MI210 has 1.33x more

Memory Bandwidth

0.53x

MI210 has 1.90x more

Google TPU v4

Compute (FP32-eq)

0.44x

TPU v4 is 2.25x faster

Pricing

Price Type	H200 SXM	MI210	TPU v4	Radeon PRO W7900
CAPEX (Street Price)	$40,000	$6,000	—	—
OPEX (per hour)	—	—	$3.00/hr	—
Price per TFLOPs (FP32-eq)	$40	$66	—	—