Compare XPUs

Select up to 5 XPUs to compare side-by-side

Select XPUs to Compare

Clear all (3)Jump to results

Filter by Vendor

Showing 72 XPUs • 3 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	Intel Data Center GPU Max 1100	NVIDIA B200
Architecture	Hopper	Ponte Vecchio	Blackwell
Form Factor	SXM	OAM	SXM
VRAM	141 GB	48 GB	192 GB
Memory Bandwidth	4,800 GB/s	1,229 GB/s	8,000 GB/s
TFLOPs (FP32)	67	22	90
TFLOPs (FP16)	1,979	177	2,250
TFLOPs	1,979	177	2,250
TFLOPs (FP8)	3,958	—	4,500
TDP	700 W	300 W	1000 W
Launch Date	Nov 2023	Jan 2023	Mar 2024

Efficiency Metrics

Metric	H200 SXM	Data Center GPU Max 1100	B200
TFLOPs per Watt (FP32-eq)	1.41	0.29	1.13
Memory Bandwidth per GB	34.0 GB/s	25.6 GB/s	41.7 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

Intel Data Center GPU Max 1100

Compute (FP32-eq)

11.18x

Need 11.18x Data Center GPU Max 1100

FP32 Compute

3.05x

Need 3.05x Data Center GPU Max 1100

VRAM

2.94x

Need 2.94x Data Center GPU Max 1100

Memory Bandwidth

3.91x

Need 3.91x Data Center GPU Max 1100

NVIDIA B200

Compute (FP32-eq)

0.88x

B200 is 1.14x faster

FP32 Compute

0.74x

B200 is 1.34x faster

VRAM

0.73x

B200 has 1.36x more

Memory Bandwidth

0.60x

B200 has 1.67x more

To match 1x Intel Data Center GPU Max 1100

NVIDIA H200 SXM

Compute (FP32-eq)

0.09x

H200 SXM is 11.18x faster

FP32 Compute

0.33x

H200 SXM is 3.05x faster

VRAM

0.34x

H200 SXM has 2.94x more

Memory Bandwidth

0.26x

H200 SXM has 3.91x more

NVIDIA B200

Compute (FP32-eq)

0.08x

B200 is 12.71x faster

FP32 Compute

0.24x

B200 is 4.09x faster

VRAM

0.25x

B200 has 4.00x more

Memory Bandwidth

0.15x

B200 has 6.51x more

To match 1x NVIDIA B200

NVIDIA H200 SXM

Compute (FP32-eq)

1.14x

Need 1.14x H200 SXM

FP32 Compute

1.34x

Need 1.34x H200 SXM

VRAM

1.36x

Need 1.36x H200 SXM

Memory Bandwidth

1.67x

Need 1.67x H200 SXM

Intel Data Center GPU Max 1100

Compute (FP32-eq)

12.71x

Need 12.71x Data Center GPU Max 1100

FP32 Compute

4.09x

Need 4.09x Data Center GPU Max 1100

VRAM

4.00x

Need 4.00x Data Center GPU Max 1100

Memory Bandwidth

6.51x

Need 6.51x Data Center GPU Max 1100

Pricing

Price Type	H200 SXM	Data Center GPU Max 1100	B200
CAPEX (Street Price)	$40,000	$5,000	$70,000
OPEX (per hour)	—	—	—
Price per TFLOPs (FP32-eq)	$40	$56	$62