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	NVIDIA H200 PCIe	NVIDIA GeForce RTX 4070 Ti
Architecture	Blackwell	Reconfigurable Dataflow Unit (RDU)	Hopper	Ada Lovelace
Form Factor	SXM	—	PCIe	PCIe
VRAM	192 GB	640 GB	141 GB	12 GB
Memory Bandwidth	8,000 GB/s	—	4,800 GB/s	504 GB/s
TFLOPs (FP32)	90	—	51	40.1
TFLOPs (FP16)	2,250	—	1,513	80.2
TFLOPs	2,250	—	1,513	80.2
TFLOPs (FP8)	4,500	—	—	—
TDP	1000 W	700 W	350 W	285 W
Launch Date	Mar 2024	Jan 2024	Mar 2024	Jan 2023

Efficiency Metrics

Metric	B200	SN40L	H200 PCIe	GeForce RTX 4070 Ti
TFLOPs per Watt (FP32-eq)	1.13	—	2.16	0.14
Memory Bandwidth per GB	41.7 GB/s	—	34.0 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

SambaNova SN40L

VRAM

0.30x

SN40L has 3.33x more

NVIDIA H200 PCIe

Compute (FP32-eq)

1.49x

Need 1.49x H200 PCIe

FP32 Compute

1.76x

Need 1.76x H200 PCIe

VRAM

1.36x

Need 1.36x H200 PCIe

Memory Bandwidth

1.67x

Need 1.67x H200 PCIe

NVIDIA GeForce RTX 4070 Ti

Compute (FP32-eq)

28.05x

Need 28.05x GeForce RTX 4070 Ti

FP32 Compute

2.24x

Need 2.24x GeForce RTX 4070 Ti

VRAM

16.00x

Need 16.00x GeForce RTX 4070 Ti

Memory Bandwidth

15.87x

Need 15.87x GeForce RTX 4070 Ti

To match 1x SambaNova SN40L

NVIDIA B200

VRAM

3.33x

Need 3.33x B200

NVIDIA H200 PCIe

VRAM

4.54x

Need 4.54x H200 PCIe

NVIDIA GeForce RTX 4070 Ti

VRAM

53.33x

Need 53.33x GeForce RTX 4070 Ti

To match 1x NVIDIA H200 PCIe

NVIDIA B200

Compute (FP32-eq)

0.67x

B200 is 1.49x faster

FP32 Compute

0.57x

B200 is 1.76x faster

VRAM

0.73x

B200 has 1.36x more

Memory Bandwidth

0.60x

B200 has 1.67x more

SambaNova SN40L

VRAM

0.22x

SN40L has 4.54x more

NVIDIA GeForce RTX 4070 Ti

Compute (FP32-eq)

18.87x

Need 18.87x GeForce RTX 4070 Ti

FP32 Compute

1.27x

Need 1.27x GeForce RTX 4070 Ti

VRAM

11.75x

Need 11.75x GeForce RTX 4070 Ti

Memory Bandwidth

9.52x

Need 9.52x GeForce RTX 4070 Ti

To match 1x NVIDIA GeForce RTX 4070 Ti

NVIDIA B200

Compute (FP32-eq)

0.04x

B200 is 28.05x faster

FP32 Compute

0.45x

B200 is 2.24x faster

VRAM

0.06x

B200 has 16.00x more

Memory Bandwidth

0.06x

B200 has 15.87x more

SambaNova SN40L

VRAM

0.02x

SN40L has 53.33x more

NVIDIA H200 PCIe

Compute (FP32-eq)

0.05x

H200 PCIe is 18.87x faster

FP32 Compute

0.79x

H200 PCIe is 1.27x faster

VRAM

0.09x

H200 PCIe has 11.75x more

Memory Bandwidth

0.10x

H200 PCIe has 9.52x more

Pricing

Price Type	B200	SN40L	H200 PCIe	GeForce RTX 4070 Ti
CAPEX (Street Price)	$70,000	—	—	—
OPEX (per hour)	—	—	—	—
Price per TFLOPs (FP32-eq)	$62	—	—	—