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 A10	Google TPU v5e	AMD MI300X	NVIDIA GeForce RTX 5080
Architecture	Ampere	TPU v5	CDNA 3	Blackwell
Form Factor	PCIe	Mezzanine	OAM	PCIe
VRAM	24 GB	—	192 GB	16 GB
Memory Bandwidth	600 GB/s	—	5,300 GB/s	960 GB/s
TFLOPs (FP32)	31.2	—	163	56.28
TFLOPs (FP16)	125	—	1,307	112.6
TFLOPs	125	197	1,307	112.6
TFLOPs (FP8)	—	—	2,614	—
TDP	150 W	250 W	750 W	360 W
Launch Date	Apr 2021	Aug 2023	Dec 2023	Jan 2025

Efficiency Metrics

Metric	A10	TPU v5e	MI300X	GeForce RTX 5080
TFLOPs per Watt (FP32-eq)	0.42	0.39	0.87	0.16
Memory Bandwidth per GB	25.0 GB/s	—	27.6 GB/s	60.0 GB/s

Performance Equivalence

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

To match 1x NVIDIA A10

Google TPU v5e

Compute (FP32-eq)

0.63x

TPU v5e is 1.58x faster

AMD MI300X

Compute (FP32-eq)

0.10x

MI300X is 10.46x faster

FP32 Compute

0.19x

MI300X is 5.22x faster

VRAM

0.13x

MI300X has 8.00x more

Memory Bandwidth

0.11x

MI300X has 8.83x more

NVIDIA GeForce RTX 5080

Compute (FP32-eq)

1.11x

Need 1.11x GeForce RTX 5080

FP32 Compute

0.55x

GeForce RTX 5080 is 1.80x faster

VRAM

1.50x

Need 1.50x GeForce RTX 5080

Memory Bandwidth

0.63x

GeForce RTX 5080 has 1.60x more

To match 1x Google TPU v5e

NVIDIA A10

Compute (FP32-eq)

1.58x

Need 1.58x A10

AMD MI300X

Compute (FP32-eq)

0.15x

MI300X is 6.63x faster

NVIDIA GeForce RTX 5080

Compute (FP32-eq)

1.75x

Need 1.75x GeForce RTX 5080

To match 1x AMD MI300X

NVIDIA A10

Compute (FP32-eq)

10.46x

Need 10.46x A10

FP32 Compute

5.22x

Need 5.22x A10

VRAM

8.00x

Need 8.00x A10

Memory Bandwidth

8.83x

Need 8.83x A10

Google TPU v5e

Compute (FP32-eq)

6.63x

Need 6.63x TPU v5e

NVIDIA GeForce RTX 5080

Compute (FP32-eq)

11.61x

Need 11.61x GeForce RTX 5080

FP32 Compute

2.90x

Need 2.90x GeForce RTX 5080

VRAM

12.00x

Need 12.00x GeForce RTX 5080

Memory Bandwidth

5.52x

Need 5.52x GeForce RTX 5080

To match 1x NVIDIA GeForce RTX 5080

NVIDIA A10

Compute (FP32-eq)

0.90x

A10 is 1.11x faster

FP32 Compute

1.80x

Need 1.80x A10

VRAM

0.67x

A10 has 1.50x more

Memory Bandwidth

1.60x

Need 1.60x A10

Google TPU v5e

Compute (FP32-eq)

0.57x

TPU v5e is 1.75x faster

AMD MI300X

Compute (FP32-eq)

0.09x

MI300X is 11.61x faster

FP32 Compute

0.35x

MI300X is 2.90x faster

VRAM

0.08x

MI300X has 12.00x more

Memory Bandwidth

0.18x

MI300X has 5.52x more

Pricing

Price Type	A10	TPU v5e	MI300X	GeForce RTX 5080
CAPEX (Street Price)	—	—	$35,000	—
OPEX (per hour)	—	$1.80/hr	$10.40/hr	—
Price per TFLOPs (FP32-eq)	—	—	$54	—