Compare XPUs

Select up to 5 XPUs to compare side-by-side

Select XPUs to Compare

Clear all (4)Jump to results
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

Meta

MTIA v1

Microsoft

Maia 100

700 TFLOPs

Moore Threads

MTT S80

NVIDIA

A10

125 TFLOPs

NVIDIA

A100 SXM

312 TFLOPs

NVIDIA

A40

150 TFLOPs

NVIDIA

B200

2,250 TFLOPs

NVIDIA

GB200 NVL72

360,000 TFLOPs

NVIDIA

GB200 Superchip

5,000 TFLOPs

NVIDIA

GeForce RTX 4060 Ti

44.2 TFLOPs

NVIDIA

GeForce RTX 4070

58.2 TFLOPs

NVIDIA

GeForce RTX 4070 Super

71 TFLOPs

NVIDIA

GeForce RTX 4070 Ti

80.2 TFLOPs

NVIDIA

GeForce RTX 4070 Ti Super

88.2 TFLOPs

NVIDIA

GeForce RTX 4080

97.5 TFLOPs

NVIDIA

GeForce RTX 4080 Super

104.4 TFLOPs

NVIDIA

GeForce RTX 4090

165.2 TFLOPs

NVIDIA

GeForce RTX 5070

61.6 TFLOPs

NVIDIA

GeForce RTX 5070 Ti

88 TFLOPs

NVIDIA

GeForce RTX 5080

112.6 TFLOPs

NVIDIA

GeForce RTX 5090

209.5 TFLOPs

NVIDIA

H100 PCIe

1,513 TFLOPs

NVIDIA

H100 SXM

1,979 TFLOPs

NVIDIA

H200 PCIe

1,513 TFLOPs

NVIDIA

H200 SXM

1,979 TFLOPs

NVIDIA

L4

121 TFLOPs

NVIDIA

L40S

733 TFLOPs

NVIDIA

RTX 4000 Ada Generation

53.4 TFLOPs

NVIDIA

RTX 5000 Ada Generation

130.6 TFLOPs

NVIDIA

RTX 6000 Ada Generation

182.2 TFLOPs

NVIDIA

RTX PRO 6000 Blackwell Max-Q

125 TFLOPs

NVIDIA

RTX PRO 6000 Blackwell Server Edition

250 TFLOPs

NVIDIA

RTX PRO 6000 Blackwell Workstation Edition

250 TFLOPs

Qualcomm

Cloud AI 100

50 TFLOPs

Rebellions

ATOM

SambaNova

SN40L

Tenstorrent

Grayskull

200 TFLOPs

Tenstorrent

Wormhole

364 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

SpecificationNVIDIA H200 SXMAMD MI325XMicrosoft Maia 100NVIDIA GeForce RTX 5090
ArchitectureHopperCDNA 3.5MaiaBlackwell
Form FactorSXMOAM—PCIe
VRAM141 GB256 GB64 GB32 GB
Memory Bandwidth4,800 GB/s6,000 GB/s—1,792 GB/s
TFLOPs (FP32)67175—104.8
TFLOPs (FP16)1,9791,400—209.5
TFLOPs1,9791,400700209.5
TFLOPs (FP8)3,9582,800——
TDP700 W800 W500 W575 W
Launch DateNov 2023Oct 2024Nov 2023Jan 2025

Efficiency Metrics

MetricH200 SXMMI325XMaia 100GeForce RTX 5090
TFLOPs per Watt (FP32-eq)1.410.880.700.18
Memory Bandwidth per GB34.0 GB/s23.4 GB/s—56.0 GB/s

Performance Equivalence

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

To match 1x NVIDIA H200 SXM

AMD MI325X
Compute (FP32-eq)
1.41x
Need 1.41x MI325X
FP32 Compute
0.38x
MI325X is 2.61x faster
VRAM
0.55x
MI325X has 1.82x more
Memory Bandwidth
0.80x
MI325X has 1.25x more
Microsoft Maia 100
Compute (FP32-eq)
2.83x
Need 2.83x Maia 100
VRAM
2.20x
Need 2.20x Maia 100
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
9.45x
Need 9.45x GeForce RTX 5090
FP32 Compute
0.64x
GeForce RTX 5090 is 1.56x faster
VRAM
4.41x
Need 4.41x GeForce RTX 5090
Memory Bandwidth
2.68x
Need 2.68x GeForce RTX 5090

To match 1x AMD MI325X

NVIDIA H200 SXM
Compute (FP32-eq)
0.71x
H200 SXM is 1.41x faster
FP32 Compute
2.61x
Need 2.61x H200 SXM
VRAM
1.82x
Need 1.82x H200 SXM
Memory Bandwidth
1.25x
Need 1.25x H200 SXM
Microsoft Maia 100
Compute (FP32-eq)
2.00x
Need 2.00x Maia 100
VRAM
4.00x
Need 4.00x Maia 100
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
6.68x
Need 6.68x GeForce RTX 5090
FP32 Compute
1.67x
Need 1.67x GeForce RTX 5090
VRAM
8.00x
Need 8.00x GeForce RTX 5090
Memory Bandwidth
3.35x
Need 3.35x GeForce RTX 5090

To match 1x Microsoft Maia 100

NVIDIA H200 SXM
Compute (FP32-eq)
0.35x
H200 SXM is 2.83x faster
VRAM
0.45x
H200 SXM has 2.20x more
AMD MI325X
Compute (FP32-eq)
0.50x
MI325X is 2.00x faster
VRAM
0.25x
MI325X has 4.00x more
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
3.34x
Need 3.34x GeForce RTX 5090
VRAM
2.00x
Need 2.00x GeForce RTX 5090

To match 1x NVIDIA GeForce RTX 5090

NVIDIA H200 SXM
Compute (FP32-eq)
0.11x
H200 SXM is 9.45x faster
FP32 Compute
1.56x
Need 1.56x H200 SXM
VRAM
0.23x
H200 SXM has 4.41x more
Memory Bandwidth
0.37x
H200 SXM has 2.68x more
AMD MI325X
Compute (FP32-eq)
0.15x
MI325X is 6.68x faster
FP32 Compute
0.60x
MI325X is 1.67x faster
VRAM
0.13x
MI325X has 8.00x more
Memory Bandwidth
0.30x
MI325X has 3.35x more
Microsoft Maia 100
Compute (FP32-eq)
0.30x
Maia 100 is 3.34x faster
VRAM
0.50x
Maia 100 has 2.00x more

Pricing

Price TypeH200 SXMMI325XMaia 100GeForce RTX 5090
CAPEX (Street Price)$40,000$45,000——
OPEX (per hour)————
Price per TFLOPs (FP32-eq)$40$64——