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 L4	NVIDIA B200	Biren Technology BR100	NVIDIA GeForce RTX 4080 Super
Architecture	Ada Lovelace	Blackwell	Biren GPU	Ada Lovelace
Form Factor	PCIe	SXM	—	PCIe
VRAM	24 GB	192 GB	64 GB	16 GB
Memory Bandwidth	300 GB/s	8,000 GB/s	—	736 GB/s
TFLOPs (FP32)	30.3	90	—	52.2
TFLOPs (FP16)	242	2,250	1,000	104.4
TFLOPs	121	2,250	—	104.4
TFLOPs (FP8)	485	4,500	—	—
TDP	72 W	1000 W	550 W	320 W
Launch Date	Mar 2023	Mar 2024	Aug 2022	Jan 2024

Efficiency Metrics

Metric	L4	B200	BR100	GeForce RTX 4080 Super
TFLOPs per Watt (FP32-eq)	0.84	1.13	—	0.16
Memory Bandwidth per GB	12.5 GB/s	41.7 GB/s	—	46.0 GB/s

Performance Equivalence

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

To match 1x NVIDIA L4

NVIDIA B200

Compute (FP32-eq)

0.05x

B200 is 18.60x faster

FP32 Compute

0.34x

B200 is 2.97x faster

VRAM

0.13x

B200 has 8.00x more

Memory Bandwidth

0.04x

B200 has 26.67x more

Biren Technology BR100

VRAM

0.38x

BR100 has 2.67x more

NVIDIA GeForce RTX 4080 Super

Compute (FP32-eq)

1.16x

Need 1.16x GeForce RTX 4080 Super

FP32 Compute

0.58x

GeForce RTX 4080 Super is 1.72x faster

VRAM

1.50x

Need 1.50x GeForce RTX 4080 Super

Memory Bandwidth

0.41x

GeForce RTX 4080 Super has 2.45x more

To match 1x NVIDIA B200

NVIDIA L4

Compute (FP32-eq)

18.60x

Need 18.60x L4

FP32 Compute

2.97x

Need 2.97x L4

VRAM

8.00x

Need 8.00x L4

Memory Bandwidth

26.67x

Need 26.67x L4

Biren Technology BR100

VRAM

3.00x

Need 3.00x BR100

NVIDIA GeForce RTX 4080 Super

Compute (FP32-eq)

21.55x

Need 21.55x GeForce RTX 4080 Super

FP32 Compute

1.72x

Need 1.72x GeForce RTX 4080 Super

VRAM

12.00x

Need 12.00x GeForce RTX 4080 Super

Memory Bandwidth

10.87x

Need 10.87x GeForce RTX 4080 Super

To match 1x Biren Technology BR100

NVIDIA L4

VRAM

2.67x

Need 2.67x L4

NVIDIA B200

VRAM

0.33x

B200 has 3.00x more

NVIDIA GeForce RTX 4080 Super

VRAM

4.00x

Need 4.00x GeForce RTX 4080 Super

To match 1x NVIDIA GeForce RTX 4080 Super

NVIDIA L4

Compute (FP32-eq)

0.86x

L4 is 1.16x faster

FP32 Compute

1.72x

Need 1.72x L4

VRAM

0.67x

L4 has 1.50x more

Memory Bandwidth

2.45x

Need 2.45x L4

NVIDIA B200

Compute (FP32-eq)

0.05x

B200 is 21.55x faster

FP32 Compute

0.58x

B200 is 1.72x faster

VRAM

0.08x

B200 has 12.00x more

Memory Bandwidth

0.09x

B200 has 10.87x more

Biren Technology BR100

VRAM

0.25x

BR100 has 4.00x more

Pricing

Price Type	L4	B200	BR100	GeForce RTX 4080 Super
CAPEX (Street Price)	$4,000	$70,000	—	—
OPEX (per hour)	$0.80/hr	—	—	—
Price per TFLOPs (FP32-eq)	$66	$62	—	—