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 B200	Moore Threads MTT S80	NVIDIA GeForce RTX 4070 Super
Architecture	Blackwell	Chunxiao	Ada Lovelace
Form Factor	SXM	—	PCIe
VRAM	192 GB	32 GB	12 GB
Memory Bandwidth	8,000 GB/s	—	504 GB/s
TFLOPs (FP32)	90	—	35.5
TFLOPs (FP16)	2,250	256	71
TFLOPs	2,250	—	71
TFLOPs (FP8)	4,500	—	—
TDP	1000 W	300 W	220 W
Launch Date	Mar 2024	Mar 2022	Jan 2024

Efficiency Metrics

Metric	B200	MTT S80	GeForce RTX 4070 Super
TFLOPs per Watt (FP32-eq)	1.13	—	0.16
Memory Bandwidth per GB	41.7 GB/s	—	42.0 GB/s

Performance Equivalence

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

To match 1x NVIDIA B200

Moore Threads MTT S80

VRAM

6.00x

Need 6.00x MTT S80

NVIDIA GeForce RTX 4070 Super

Compute (FP32-eq)

31.69x

Need 31.69x GeForce RTX 4070 Super

FP32 Compute

2.54x

Need 2.54x GeForce RTX 4070 Super

VRAM

16.00x

Need 16.00x GeForce RTX 4070 Super

Memory Bandwidth

15.87x

Need 15.87x GeForce RTX 4070 Super

To match 1x Moore Threads MTT S80

NVIDIA B200

VRAM

0.17x

B200 has 6.00x more

NVIDIA GeForce RTX 4070 Super

VRAM

2.67x

Need 2.67x GeForce RTX 4070 Super

To match 1x NVIDIA GeForce RTX 4070 Super

NVIDIA B200

Compute (FP32-eq)

0.03x

B200 is 31.69x faster

FP32 Compute

0.39x

B200 is 2.54x faster

VRAM

0.06x

B200 has 16.00x more

Memory Bandwidth

0.06x

B200 has 15.87x more

Moore Threads MTT S80

VRAM

0.38x

MTT S80 has 2.67x more

Pricing

Price Type	B200	MTT S80	GeForce RTX 4070 Super
CAPEX (Street Price)	$70,000	—	—
OPEX (per hour)	—	—	—
Price per TFLOPs (FP32-eq)	$62	—	—