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

SpecificationAMD MI325XAWS Trainium2NVIDIA GB200 SuperchipNVIDIA GeForce RTX 4080 Super
ArchitectureCDNA 3.5Trainium Gen2BlackwellAda Lovelace
Form FactorOAM—SXMPCIe
VRAM256 GB—384 GB16 GB
Memory Bandwidth6,000 GB/s—8,000 GB/s736 GB/s
TFLOPs (FP32)175—9052.2
TFLOPs (FP16)1,400—5,000104.4
TFLOPs1,4006805,000104.4
TFLOPs (FP8)2,800———
TDP800 W300 W2700 W320 W
Launch DateOct 2024Nov 2023Mar 2024Jan 2024

Efficiency Metrics

MetricMI325XTrainium2GB200 SuperchipGeForce RTX 4080 Super
TFLOPs per Watt (FP32-eq)0.881.130.930.16
Memory Bandwidth per GB23.4 GB/s—20.8 GB/s46.0 GB/s

Performance Equivalence

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

To match 1x AMD MI325X

AWS Trainium2
Compute (FP32-eq)
2.06x
Need 2.06x Trainium2
NVIDIA GB200 Superchip
Compute (FP32-eq)
0.28x
GB200 Superchip is 3.57x faster
FP32 Compute
1.94x
Need 1.94x GB200 Superchip
VRAM
0.67x
GB200 Superchip has 1.50x more
Memory Bandwidth
0.75x
GB200 Superchip has 1.33x more
NVIDIA GeForce RTX 4080 Super
Compute (FP32-eq)
13.41x
Need 13.41x GeForce RTX 4080 Super
FP32 Compute
3.35x
Need 3.35x GeForce RTX 4080 Super
VRAM
16.00x
Need 16.00x GeForce RTX 4080 Super
Memory Bandwidth
8.15x
Need 8.15x GeForce RTX 4080 Super

To match 1x AWS Trainium2

AMD MI325X
Compute (FP32-eq)
0.49x
MI325X is 2.06x faster
NVIDIA GB200 Superchip
Compute (FP32-eq)
0.14x
GB200 Superchip is 7.35x faster
NVIDIA GeForce RTX 4080 Super
Compute (FP32-eq)
6.51x
Need 6.51x GeForce RTX 4080 Super

To match 1x NVIDIA GB200 Superchip

AMD MI325X
Compute (FP32-eq)
3.57x
Need 3.57x MI325X
FP32 Compute
0.51x
MI325X is 1.94x faster
VRAM
1.50x
Need 1.50x MI325X
Memory Bandwidth
1.33x
Need 1.33x MI325X
AWS Trainium2
Compute (FP32-eq)
7.35x
Need 7.35x Trainium2
NVIDIA GeForce RTX 4080 Super
Compute (FP32-eq)
47.89x
Need 47.89x GeForce RTX 4080 Super
FP32 Compute
1.72x
Need 1.72x GeForce RTX 4080 Super
VRAM
24.00x
Need 24.00x GeForce RTX 4080 Super
Memory Bandwidth
10.87x
Need 10.87x GeForce RTX 4080 Super

To match 1x NVIDIA GeForce RTX 4080 Super

AMD MI325X
Compute (FP32-eq)
0.07x
MI325X is 13.41x faster
FP32 Compute
0.30x
MI325X is 3.35x faster
VRAM
0.06x
MI325X has 16.00x more
Memory Bandwidth
0.12x
MI325X has 8.15x more
AWS Trainium2
Compute (FP32-eq)
0.15x
Trainium2 is 6.51x faster
NVIDIA GB200 Superchip
Compute (FP32-eq)
0.02x
GB200 Superchip is 47.89x faster
FP32 Compute
0.58x
GB200 Superchip is 1.72x faster
VRAM
0.04x
GB200 Superchip has 24.00x more
Memory Bandwidth
0.09x
GB200 Superchip has 10.87x more

Pricing

Price TypeMI325XTrainium2GB200 SuperchipGeForce RTX 4080 Super
CAPEX (Street Price)$45,000———
OPEX (per hour)—$1.34/hr——
Price per TFLOPs (FP32-eq)$64———