Compare XPUs

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

Select XPUs to Compare

Clear all (5)Jump to results
Showing 72 XPUs • 5 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

Maximum of 5 XPUs can be compared at once. Deselect one to add another.

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 MI250XNVIDIA GB200 SuperchipAMD MI300AEtched Sohu
ArchitectureHopperCDNA 2BlackwellCDNA 3Transformer ASIC
Form FactorSXMOAMSXMOAMPCIe
VRAM141 GB128 GB384 GB128 GB144 GB
Memory Bandwidth4,800 GB/s3,277 GB/s8,000 GB/s5,300 GB/s4,800 GB/s
TFLOPs (FP32)6747.990122.610,000
TFLOPs (FP16)1,9793835,000980.6—
TFLOPs1,9793835,000980.610,000
TFLOPs (FP8)3,958————
TDP700 W560 W2700 W760 W700 W
Launch DateNov 2023Nov 2021Mar 2024Dec 2023Jun 2024

Efficiency Metrics

MetricH200 SXMMI250XGB200 SuperchipMI300ASohu
TFLOPs per Watt (FP32-eq)1.410.340.930.6514.29
Memory Bandwidth per GB34.0 GB/s25.6 GB/s20.8 GB/s41.4 GB/s33.3 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 MI250X
Compute (FP32-eq)
5.17x
Need 5.17x MI250X
FP32 Compute
1.40x
Need 1.40x MI250X
VRAM
1.10x
Need 1.10x MI250X
Memory Bandwidth
1.46x
Need 1.46x MI250X
NVIDIA GB200 Superchip
Compute (FP32-eq)
0.40x
GB200 Superchip is 2.53x faster
FP32 Compute
0.74x
GB200 Superchip is 1.34x faster
VRAM
0.37x
GB200 Superchip has 2.72x more
Memory Bandwidth
0.60x
GB200 Superchip has 1.67x more
AMD MI300A
Compute (FP32-eq)
2.02x
Need 2.02x MI300A
FP32 Compute
0.55x
MI300A is 1.83x faster
VRAM
1.10x
Need 1.10x MI300A
Memory Bandwidth
0.91x
MI300A has 1.10x more
Etched Sohu
Compute (FP32-eq)
0.10x
Sohu is 10.11x faster
FP32 Compute
0.01x
Sohu is 149.25x faster
VRAM
0.98x
Sohu has 1.02x more
Memory Bandwidth
1.00x
Sohu has 1.00x more

To match 1x AMD MI250X

NVIDIA H200 SXM
Compute (FP32-eq)
0.19x
H200 SXM is 5.17x faster
FP32 Compute
0.71x
H200 SXM is 1.40x faster
VRAM
0.91x
H200 SXM has 1.10x more
Memory Bandwidth
0.68x
H200 SXM has 1.46x more
NVIDIA GB200 Superchip
Compute (FP32-eq)
0.08x
GB200 Superchip is 13.05x faster
FP32 Compute
0.53x
GB200 Superchip is 1.88x faster
VRAM
0.33x
GB200 Superchip has 3.00x more
Memory Bandwidth
0.41x
GB200 Superchip has 2.44x more
AMD MI300A
Compute (FP32-eq)
0.39x
MI300A is 2.56x faster
FP32 Compute
0.39x
MI300A is 2.56x faster
VRAM
1.00x
MI300A has 1.00x more
Memory Bandwidth
0.62x
MI300A has 1.62x more
Etched Sohu
Compute (FP32-eq)
0.02x
Sohu is 52.22x faster
FP32 Compute
0.00x
Sohu is 208.77x faster
VRAM
0.89x
Sohu has 1.13x more
Memory Bandwidth
0.68x
Sohu has 1.46x more

To match 1x NVIDIA GB200 Superchip

NVIDIA H200 SXM
Compute (FP32-eq)
2.53x
Need 2.53x H200 SXM
FP32 Compute
1.34x
Need 1.34x H200 SXM
VRAM
2.72x
Need 2.72x H200 SXM
Memory Bandwidth
1.67x
Need 1.67x H200 SXM
AMD MI250X
Compute (FP32-eq)
13.05x
Need 13.05x MI250X
FP32 Compute
1.88x
Need 1.88x MI250X
VRAM
3.00x
Need 3.00x MI250X
Memory Bandwidth
2.44x
Need 2.44x MI250X
AMD MI300A
Compute (FP32-eq)
5.10x
Need 5.10x MI300A
FP32 Compute
0.73x
MI300A is 1.36x faster
VRAM
3.00x
Need 3.00x MI300A
Memory Bandwidth
1.51x
Need 1.51x MI300A
Etched Sohu
Compute (FP32-eq)
0.25x
Sohu is 4.00x faster
FP32 Compute
0.01x
Sohu is 111.11x faster
VRAM
2.67x
Need 2.67x Sohu
Memory Bandwidth
1.67x
Need 1.67x Sohu

To match 1x AMD MI300A

NVIDIA H200 SXM
Compute (FP32-eq)
0.50x
H200 SXM is 2.02x faster
FP32 Compute
1.83x
Need 1.83x H200 SXM
VRAM
0.91x
H200 SXM has 1.10x more
Memory Bandwidth
1.10x
Need 1.10x H200 SXM
AMD MI250X
Compute (FP32-eq)
2.56x
Need 2.56x MI250X
FP32 Compute
2.56x
Need 2.56x MI250X
VRAM
1.00x
MI250X has 1.00x more
Memory Bandwidth
1.62x
Need 1.62x MI250X
NVIDIA GB200 Superchip
Compute (FP32-eq)
0.20x
GB200 Superchip is 5.10x faster
FP32 Compute
1.36x
Need 1.36x GB200 Superchip
VRAM
0.33x
GB200 Superchip has 3.00x more
Memory Bandwidth
0.66x
GB200 Superchip has 1.51x more
Etched Sohu
Compute (FP32-eq)
0.05x
Sohu is 20.40x faster
FP32 Compute
0.01x
Sohu is 81.57x faster
VRAM
0.89x
Sohu has 1.13x more
Memory Bandwidth
1.10x
Need 1.10x Sohu

To match 1x Etched Sohu

NVIDIA H200 SXM
Compute (FP32-eq)
10.11x
Need 10.11x H200 SXM
FP32 Compute
149.25x
Need 149.25x H200 SXM
VRAM
1.02x
Need 1.02x H200 SXM
Memory Bandwidth
1.00x
H200 SXM has 1.00x more
AMD MI250X
Compute (FP32-eq)
52.22x
Need 52.22x MI250X
FP32 Compute
208.77x
Need 208.77x MI250X
VRAM
1.13x
Need 1.13x MI250X
Memory Bandwidth
1.46x
Need 1.46x MI250X
NVIDIA GB200 Superchip
Compute (FP32-eq)
4.00x
Need 4.00x GB200 Superchip
FP32 Compute
111.11x
Need 111.11x GB200 Superchip
VRAM
0.38x
GB200 Superchip has 2.67x more
Memory Bandwidth
0.60x
GB200 Superchip has 1.67x more
AMD MI300A
Compute (FP32-eq)
20.40x
Need 20.40x MI300A
FP32 Compute
81.57x
Need 81.57x MI300A
VRAM
1.13x
Need 1.13x MI300A
Memory Bandwidth
0.91x
MI300A has 1.10x more

Pricing

Price TypeH200 SXMMI250XGB200 SuperchipMI300ASohu
CAPEX (Street Price)$40,000$12,000———
OPEX (per hour)—$2.00/hr———
Price per TFLOPs (FP32-eq)$40$63———