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 128 XPUs • 3 selected

Alibaba

Hanguang 800

AMD

MI100

23.1 TFLOPs

AMD

MI210

181 TFLOPs

AMD

MI250X

383 TFLOPs

AMD

MI300X

1,307 TFLOPs

AMD

MI325X

1,400 TFLOPs

AMD

MI350X

2,100 TFLOPs

AMD

MI355X

5,300 TFLOPs

AMD

Radeon Pro V520

23.04 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

FuriosaAI

RNGD (Renegade)

256 TFLOPs

FuriosaAI

Warboy

Google

TPU v4

275 TFLOPs

Google

TPU v5e

197 TFLOPs

Google

TPU v5p

459 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 RTX 4500 Ada Generation	NVIDIA GeForce RTX 4090	NVIDIA A100 SXM
Architecture	Ada Lovelace	Ada Lovelace	Ampere
Form Factor	PCIe	PCIe	SXM
VRAM	24 GB	24 GB	80 GB
Memory Bandwidth	576 GB/s	1,008 GB/s	2,039 GB/s
TFLOPs (FP32)	48.5	82.6	19.5
TFLOPs (FP16)	—	—	312
TFLOPs	97	165.2	312
TFLOPs (FP8)	—	—	—
TDP	210 W	450 W	400 W
Launch Date	Mar 2023	Oct 2022	May 2020

Efficiency Metrics

Metric	RTX 4500 Ada Generation	GeForce RTX 4090	A100 SXM
TFLOPs per Watt (FP32-eq)	0.23	0.18	0.39
Memory Bandwidth per GB	24.0 GB/s	42.0 GB/s	25.5 GB/s

Performance Equivalence

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

To match 1x NVIDIA RTX 4500 Ada Generation

NVIDIA GeForce RTX 4090

Compute (FP32-eq)

0.59x

GeForce RTX 4090 is 1.70x faster

FP32 Compute

0.59x

GeForce RTX 4090 is 1.70x faster

VRAM

1.00x

GeForce RTX 4090 has 1.00x more

Memory Bandwidth

0.57x

GeForce RTX 4090 has 1.75x more

NVIDIA A100 SXM

Compute (FP32-eq)

0.31x

A100 SXM is 3.22x faster

FP32 Compute

2.49x

Need 2.49x A100 SXM

VRAM

0.30x

A100 SXM has 3.33x more

Memory Bandwidth

0.28x

A100 SXM has 3.54x more

To match 1x NVIDIA GeForce RTX 4090

NVIDIA RTX 4500 Ada Generation

Compute (FP32-eq)

1.70x

Need 1.70x RTX 4500 Ada Generation

FP32 Compute

1.70x

Need 1.70x RTX 4500 Ada Generation

VRAM

1.00x

RTX 4500 Ada Generation has 1.00x more

Memory Bandwidth

1.75x

Need 1.75x RTX 4500 Ada Generation

NVIDIA A100 SXM

Compute (FP32-eq)

0.53x

A100 SXM is 1.89x faster

FP32 Compute

4.24x

Need 4.24x A100 SXM

VRAM

0.30x

A100 SXM has 3.33x more

Memory Bandwidth

0.49x

A100 SXM has 2.02x more

To match 1x NVIDIA A100 SXM

NVIDIA RTX 4500 Ada Generation

Compute (FP32-eq)

3.22x

Need 3.22x RTX 4500 Ada Generation

FP32 Compute

0.40x

RTX 4500 Ada Generation is 2.49x faster

VRAM

3.33x

Need 3.33x RTX 4500 Ada Generation

Memory Bandwidth

3.54x

Need 3.54x RTX 4500 Ada Generation

NVIDIA GeForce RTX 4090

Compute (FP32-eq)

1.89x

Need 1.89x GeForce RTX 4090

FP32 Compute

0.24x

GeForce RTX 4090 is 4.24x faster

VRAM

3.33x

Need 3.33x GeForce RTX 4090

Memory Bandwidth

2.02x

Need 2.02x GeForce RTX 4090

Pricing

Price Type	RTX 4500 Ada Generation	GeForce RTX 4090	A100 SXM
CAPEX (Street Price)	—	—	$15,000
OPEX (per hour)	—	$0.18/hr	$4.05/hr
Price per TFLOPs (FP32-eq)	—	—	$96