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 A10	NVIDIA B200	AWS Inferentia2	NVIDIA H100 PCIe
Architecture	Ampere	Blackwell	Inferentia Gen2	Hopper
Form Factor	PCIe	SXM	—	PCIe
VRAM	24 GB	192 GB	32 GB	80 GB
Memory Bandwidth	600 GB/s	8,000 GB/s	—	2,000 GB/s
TFLOPs (FP32)	31.2	90	—	51
TFLOPs (FP16)	125	2,250	—	1,513
TFLOPs	125	2,250	190	1,513
TFLOPs (FP8)	—	4,500	—	—
TDP	150 W	1000 W	150 W	350 W
Launch Date	Apr 2021	Mar 2024	Nov 2022	Sep 2022

Efficiency Metrics

Metric	A10	B200	Inferentia2	H100 PCIe
TFLOPs per Watt (FP32-eq)	0.42	1.13	0.63	2.16
Memory Bandwidth per GB	25.0 GB/s	41.7 GB/s	—	25.0 GB/s

Performance Equivalence

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

To match 1x NVIDIA A10

NVIDIA B200

Compute (FP32-eq)

0.06x

B200 is 18.00x faster

FP32 Compute

0.35x

B200 is 2.88x faster

VRAM

0.13x

B200 has 8.00x more

Memory Bandwidth

0.07x

B200 has 13.33x more

AWS Inferentia2

Compute (FP32-eq)

0.66x

Inferentia2 is 1.52x faster

VRAM

0.75x

Inferentia2 has 1.33x more

NVIDIA H100 PCIe

Compute (FP32-eq)

0.08x

H100 PCIe is 12.10x faster

FP32 Compute

0.61x

H100 PCIe is 1.63x faster

VRAM

0.30x

H100 PCIe has 3.33x more

Memory Bandwidth

0.30x

H100 PCIe has 3.33x more

To match 1x NVIDIA B200

NVIDIA A10

Compute (FP32-eq)

18.00x

Need 18.00x A10

FP32 Compute

2.88x

Need 2.88x A10

VRAM

8.00x

Need 8.00x A10

Memory Bandwidth

13.33x

Need 13.33x A10

AWS Inferentia2

Compute (FP32-eq)

11.84x

Need 11.84x Inferentia2

VRAM

6.00x

Need 6.00x Inferentia2

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

To match 1x AWS Inferentia2

NVIDIA A10

Compute (FP32-eq)

1.52x

Need 1.52x A10

VRAM

1.33x

Need 1.33x A10

NVIDIA B200

Compute (FP32-eq)

0.08x

B200 is 11.84x faster

VRAM

0.17x

B200 has 6.00x more

NVIDIA H100 PCIe

Compute (FP32-eq)

0.13x

H100 PCIe is 7.96x faster

VRAM

0.40x

H100 PCIe has 2.50x more

To match 1x NVIDIA H100 PCIe

NVIDIA A10

Compute (FP32-eq)

12.10x

Need 12.10x A10

FP32 Compute

1.63x

Need 1.63x A10

VRAM

3.33x

Need 3.33x A10

Memory Bandwidth

3.33x

Need 3.33x A10

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

AWS Inferentia2

Compute (FP32-eq)

7.96x

Need 7.96x Inferentia2

VRAM

2.50x

Need 2.50x Inferentia2

Pricing

Price Type	A10	B200	Inferentia2	H100 PCIe
CAPEX (Street Price)	—	$70,000	—	—
OPEX (per hour)	—	—	—	—
Price per TFLOPs (FP32-eq)	—	$62	—	—