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 B200	AMD MI350X	Cambricon MLU370	NVIDIA RTX 6000 Ada Generation
Architecture	Blackwell	CDNA 4	MLU Core	Ada Lovelace
Form Factor	SXM	OAM	—	PCIe
VRAM	192 GB	288 GB	48 GB	48 GB
Memory Bandwidth	8,000 GB/s	—	—	960 GB/s
TFLOPs (FP32)	90	—	—	91.1
TFLOPs (FP16)	2,250	—	—	182.2
TFLOPs	2,250	2,100	256	182.2
TFLOPs (FP8)	4,500	—	—	—
TDP	1000 W	850 W	300 W	300 W
Launch Date	Mar 2024	Jun 2025	Nov 2022	Dec 2022

Efficiency Metrics

Metric	B200	MI350X	MLU370	RTX 6000 Ada Generation
TFLOPs per Watt (FP32-eq)	1.13	1.24	0.43	0.30
Memory Bandwidth per GB	41.7 GB/s	—	—	20.0 GB/s

Performance Equivalence

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

To match 1x NVIDIA B200

AMD MI350X

Compute (FP32-eq)

1.07x

Need 1.07x MI350X

VRAM

0.67x

MI350X has 1.50x more

Cambricon MLU370

Compute (FP32-eq)

8.79x

Need 8.79x MLU370

VRAM

4.00x

Need 4.00x MLU370

NVIDIA RTX 6000 Ada Generation

Compute (FP32-eq)

12.35x

Need 12.35x RTX 6000 Ada Generation

FP32 Compute

0.99x

RTX 6000 Ada Generation is 1.01x faster

VRAM

4.00x

Need 4.00x RTX 6000 Ada Generation

Memory Bandwidth

8.33x

Need 8.33x RTX 6000 Ada Generation

To match 1x AMD MI350X

NVIDIA B200

Compute (FP32-eq)

0.93x

B200 is 1.07x faster

VRAM

1.50x

Need 1.50x B200

Cambricon MLU370

Compute (FP32-eq)

8.20x

Need 8.20x MLU370

VRAM

6.00x

Need 6.00x MLU370

NVIDIA RTX 6000 Ada Generation

Compute (FP32-eq)

11.53x

Need 11.53x RTX 6000 Ada Generation

VRAM

6.00x

Need 6.00x RTX 6000 Ada Generation

To match 1x Cambricon MLU370

NVIDIA B200

Compute (FP32-eq)

0.11x

B200 is 8.79x faster

VRAM

0.25x

B200 has 4.00x more

AMD MI350X

Compute (FP32-eq)

0.12x

MI350X is 8.20x faster

VRAM

0.17x

MI350X has 6.00x more

NVIDIA RTX 6000 Ada Generation

Compute (FP32-eq)

1.41x

Need 1.41x RTX 6000 Ada Generation

VRAM

1.00x

RTX 6000 Ada Generation has 1.00x more

To match 1x NVIDIA RTX 6000 Ada Generation

NVIDIA B200

Compute (FP32-eq)

0.08x

B200 is 12.35x faster

FP32 Compute

1.01x

Need 1.01x B200

VRAM

0.25x

B200 has 4.00x more

Memory Bandwidth

0.12x

B200 has 8.33x more

AMD MI350X

Compute (FP32-eq)

0.09x

MI350X is 11.53x faster

VRAM

0.17x

MI350X has 6.00x more

Cambricon MLU370

Compute (FP32-eq)

0.71x

MLU370 is 1.41x faster

VRAM

1.00x

MLU370 has 1.00x more

Pricing

Price Type	B200	MI350X	MLU370	RTX 6000 Ada Generation
CAPEX (Street Price)	$70,000	—	—	—
OPEX (per hour)	—	—	—	—
Price per TFLOPs (FP32-eq)	$62	—	—	—