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	SambaNova SN40L	AWS Inferentia2	NVIDIA GeForce RTX 4060 Ti
Architecture	Blackwell	Reconfigurable Dataflow Unit (RDU)	Inferentia Gen2	Ada Lovelace
Form Factor	SXM	—	—	PCIe
VRAM	192 GB	640 GB	32 GB	8 GB
Memory Bandwidth	8,000 GB/s	—	—	288 GB/s
TFLOPs (FP32)	90	—	—	22.1
TFLOPs (FP16)	2,250	—	—	44.2
TFLOPs	2,250	—	190	44.2
TFLOPs (FP8)	4,500	—	—	—
TDP	1000 W	700 W	150 W	160 W
Launch Date	Mar 2024	Jan 2024	Nov 2022	May 2023

Efficiency Metrics

Metric	B200	SN40L	Inferentia2	GeForce RTX 4060 Ti
TFLOPs per Watt (FP32-eq)	1.13	—	0.63	0.14
Memory Bandwidth per GB	41.7 GB/s	—	—	36.0 GB/s

Performance Equivalence

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

To match 1x NVIDIA B200

SambaNova SN40L

VRAM

0.30x

SN40L has 3.33x more

AWS Inferentia2

Compute (FP32-eq)

11.84x

Need 11.84x Inferentia2

VRAM

6.00x

Need 6.00x Inferentia2

NVIDIA GeForce RTX 4060 Ti

Compute (FP32-eq)

50.90x

Need 50.90x GeForce RTX 4060 Ti

FP32 Compute

4.07x

Need 4.07x GeForce RTX 4060 Ti

VRAM

24.00x

Need 24.00x GeForce RTX 4060 Ti

Memory Bandwidth

27.78x

Need 27.78x GeForce RTX 4060 Ti

To match 1x SambaNova SN40L

NVIDIA B200

VRAM

3.33x

Need 3.33x B200

AWS Inferentia2

VRAM

20.00x

Need 20.00x Inferentia2

NVIDIA GeForce RTX 4060 Ti

VRAM

80.00x

Need 80.00x GeForce RTX 4060 Ti

To match 1x AWS Inferentia2

NVIDIA B200

Compute (FP32-eq)

0.08x

B200 is 11.84x faster

VRAM

0.17x

B200 has 6.00x more

SambaNova SN40L

VRAM

0.05x

SN40L has 20.00x more

NVIDIA GeForce RTX 4060 Ti

Compute (FP32-eq)

4.30x

Need 4.30x GeForce RTX 4060 Ti

VRAM

4.00x

Need 4.00x GeForce RTX 4060 Ti

To match 1x NVIDIA GeForce RTX 4060 Ti

NVIDIA B200

Compute (FP32-eq)

0.02x

B200 is 50.90x faster

FP32 Compute

0.25x

B200 is 4.07x faster

VRAM

0.04x

B200 has 24.00x more

Memory Bandwidth

0.04x

B200 has 27.78x more

SambaNova SN40L

VRAM

0.01x

SN40L has 80.00x more

AWS Inferentia2

Compute (FP32-eq)

0.23x

Inferentia2 is 4.30x faster

VRAM

0.25x

Inferentia2 has 4.00x more

Pricing

Price Type	B200	SN40L	Inferentia2	GeForce RTX 4060 Ti
CAPEX (Street Price)	$70,000	—	—	—
OPEX (per hour)	—	—	—	—
Price per TFLOPs (FP32-eq)	$62	—	—	—