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	Intel Data Center GPU Max 1550	NVIDIA GeForce RTX 4070	AMD MI300A
Architecture	Ponte Vecchio	Ada Lovelace	CDNA 3
Form Factor	OAM	PCIe	OAM
VRAM	128 GB	12 GB	128 GB
Memory Bandwidth	3,277 GB/s	504 GB/s	5,300 GB/s
TFLOPs (FP32)	52	29.1	122.6
TFLOPs (FP16)	419	58.2	980.6
TFLOPs	419	58.2	980.6
TFLOPs (FP8)	—	—	—
TDP	600 W	200 W	760 W
Launch Date	Jan 2023	Apr 2023	Dec 2023

Efficiency Metrics

Metric	Data Center GPU Max 1550	GeForce RTX 4070	MI300A
TFLOPs per Watt (FP32-eq)	0.35	0.15	0.65
Memory Bandwidth per GB	25.6 GB/s	42.0 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 Intel Data Center GPU Max 1550

NVIDIA GeForce RTX 4070

Compute (FP32-eq)

7.20x

Need 7.20x GeForce RTX 4070

FP32 Compute

1.79x

Need 1.79x GeForce RTX 4070

VRAM

10.67x

Need 10.67x GeForce RTX 4070

Memory Bandwidth

6.50x

Need 6.50x GeForce RTX 4070

AMD MI300A

Compute (FP32-eq)

0.43x

MI300A is 2.34x faster

FP32 Compute

0.42x

MI300A is 2.36x faster

VRAM

1.00x

MI300A has 1.00x more

Memory Bandwidth

0.62x

MI300A has 1.62x more

To match 1x NVIDIA GeForce RTX 4070

Intel Data Center GPU Max 1550

Compute (FP32-eq)

0.14x

Data Center GPU Max 1550 is 7.20x faster

FP32 Compute

0.56x

Data Center GPU Max 1550 is 1.79x faster

VRAM

0.09x

Data Center GPU Max 1550 has 10.67x more

Memory Bandwidth

0.15x

Data Center GPU Max 1550 has 6.50x more

AMD MI300A

Compute (FP32-eq)

0.06x

MI300A is 16.85x faster

FP32 Compute

0.24x

MI300A is 4.21x faster

VRAM

0.09x

MI300A has 10.67x more

Memory Bandwidth

0.10x

MI300A has 10.52x more

To match 1x AMD MI300A

Intel Data Center GPU Max 1550

Compute (FP32-eq)

2.34x

Need 2.34x Data Center GPU Max 1550

FP32 Compute

2.36x

Need 2.36x Data Center GPU Max 1550

VRAM

1.00x

Data Center GPU Max 1550 has 1.00x more

Memory Bandwidth

1.62x

Need 1.62x Data Center GPU Max 1550

NVIDIA GeForce RTX 4070

Compute (FP32-eq)

16.85x

Need 16.85x GeForce RTX 4070

FP32 Compute

4.21x

Need 4.21x GeForce RTX 4070

VRAM

10.67x

Need 10.67x GeForce RTX 4070

Memory Bandwidth

10.52x

Need 10.52x GeForce RTX 4070

Pricing

Price Type	Data Center GPU Max 1550	GeForce RTX 4070	MI300A
CAPEX (Street Price)	$10,000	—	—
OPEX (per hour)	—	—	—
Price per TFLOPs (FP32-eq)	$48	—	—