Compare XPUs

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

Select XPUs to Compare

Clear all (6)Jump to results
Showing 128 XPUs • 6 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

Meta

MTIA v1

Microsoft

Maia 100

700 TFLOPs

Moore Threads

MTT S80

NVIDIA

A10

125 TFLOPs

NVIDIA

A100 SXM

312 TFLOPs

NVIDIA

A10G

125 TFLOPs

NVIDIA

A16

71.2 TFLOPs

NVIDIA

A30

165 TFLOPs

NVIDIA

A40

150 TFLOPs

NVIDIA

A800

312 TFLOPs

NVIDIA

B100

1,800 TFLOPs

NVIDIA

B200

2,250 TFLOPs

NVIDIA

GB200

2,500 TFLOPs

NVIDIA

GeForce GT 710

0.366 TFLOPs

NVIDIA

GeForce GT 730

0.693 TFLOPs

NVIDIA

GeForce GTX 1050 Ti

2.138 TFLOPs

NVIDIA

GeForce GTX 1060

4.375 TFLOPs

NVIDIA

GeForce GTX 1070

6.463 TFLOPs

NVIDIA

GeForce GTX 1070 Ti

8.186 TFLOPs

NVIDIA

GeForce GTX 1080

8.873 TFLOPs

NVIDIA

GeForce GTX 1080 Ti

11.34 TFLOPs

NVIDIA

GeForce GTX 1650

2.984 TFLOPs

NVIDIA

GeForce GTX 1660

5.027 TFLOPs

NVIDIA

GeForce GTX 1660 Super

5.027 TFLOPs

NVIDIA

GeForce RTX 2060

6.5 TFLOPs

NVIDIA

GeForce RTX 2060 Super

7.2 TFLOPs

NVIDIA

GeForce RTX 2070

7.5 TFLOPs

NVIDIA

GeForce RTX 2080

10.1 TFLOPs

NVIDIA

GeForce RTX 2080 Ti

13.4 TFLOPs

NVIDIA

GeForce RTX 3050

18.2 TFLOPs

NVIDIA

GeForce RTX 3060

25.4 TFLOPs

NVIDIA

GeForce RTX 3060 Ti

33.2 TFLOPs

NVIDIA

GeForce RTX 3070

40.5 TFLOPs

NVIDIA

GeForce RTX 3070 Ti

43.2 TFLOPs

NVIDIA

GeForce RTX 3080

59.2 TFLOPs

NVIDIA

GeForce RTX 3080 Ti

68.4 TFLOPs

NVIDIA

GeForce RTX 3090

71 TFLOPs

NVIDIA

GeForce RTX 3090 Ti

80 TFLOPs

NVIDIA

GeForce RTX 4060

30 TFLOPs

NVIDIA

GeForce RTX 4060 Ti

44 TFLOPs

NVIDIA

GeForce RTX 4060 Ti 16GB

44 TFLOPs

NVIDIA

GeForce RTX 4070

58.92 TFLOPs

NVIDIA

GeForce RTX 4070 Super

70 TFLOPs

NVIDIA

GeForce RTX 4070 Ti

80.16 TFLOPs

NVIDIA

GeForce RTX 4070 Ti Super

88 TFLOPs

NVIDIA

GeForce RTX 4080

97.76 TFLOPs

NVIDIA

GeForce RTX 4080 Super

104 TFLOPs

NVIDIA

GeForce RTX 4090

165.2 TFLOPs

NVIDIA

GeForce RTX 4090 D

165 TFLOPs

NVIDIA

GeForce RTX 5060

60 TFLOPs

NVIDIA

GeForce RTX 5060 Ti

88 TFLOPs

NVIDIA

GeForce RTX 5070

110 TFLOPs

NVIDIA

GeForce RTX 5070 Ti

133 TFLOPs

NVIDIA

GeForce RTX 5080

171 TFLOPs

NVIDIA

GeForce RTX 5090

318 TFLOPs

NVIDIA

GH200

989 TFLOPs

NVIDIA

H100 SXM

1,979 TFLOPs

NVIDIA

H200 SXM

1,979 TFLOPs

NVIDIA

K80

8.73 TFLOPs

NVIDIA

L4

121 TFLOPs

NVIDIA

L40

181.05 TFLOPs

NVIDIA

L40S

733 TFLOPs

NVIDIA

P100

9.3 TFLOPs

NVIDIA

P4

5.5 TFLOPs

NVIDIA

P40

12 TFLOPs

NVIDIA

Quadro K620

0.768 TFLOPs

NVIDIA

Quadro M4000

2.57 TFLOPs

NVIDIA

Quadro M60

4.825 TFLOPs

NVIDIA

Quadro P1000

1.894 TFLOPs

NVIDIA

Quadro P4000

5.304 TFLOPs

NVIDIA

Quadro P5000

8.873 TFLOPs

NVIDIA

Quadro P600

1.117 TFLOPs

NVIDIA

Quadro P6000

12.63 TFLOPs

NVIDIA

Quadro P620

1.386 TFLOPs

NVIDIA

Quadro RTX 6000

130.5 TFLOPs

NVIDIA

RTX 4000

57.6 TFLOPs

NVIDIA

RTX 4000 SFF Ada Generation

52 TFLOPs

NVIDIA

RTX 4500 Ada Generation

97 TFLOPs

NVIDIA

RTX 5000

89.2 TFLOPs

NVIDIA

RTX 5000 Ada Generation

130 TFLOPs

NVIDIA

RTX 5000 Blackwell

242 TFLOPs

NVIDIA

RTX 5880 Ada Generation

167 TFLOPs

NVIDIA

RTX 6000 Ada Generation

182.5 TFLOPs

NVIDIA

RTX 6000 Blackwell

362 TFLOPs

NVIDIA

RTX A2000

16 TFLOPs

NVIDIA

RTX A4000

38.7 TFLOPs

NVIDIA

RTX A4500

46.6 TFLOPs

NVIDIA

RTX A5000

54.2 TFLOPs

NVIDIA

RTX A6000

77.9 TFLOPs

NVIDIA

T1000

2.5 TFLOPs

NVIDIA

T4

65 TFLOPs

NVIDIA

T4G

65 TFLOPs

NVIDIA

V100S

16.4 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

SpecificationIntel Habana Gaudi 2NVIDIA L4NVIDIA GeForce RTX 4090NVIDIA Quadro K620NVIDIA GeForce RTX 3090NVIDIA V100S
ArchitectureGaudi Gen2Ada LovelaceAda LovelaceKeplerAmpereVolta
Form FactorOAMPCIePCIePCIePCIePCIe
VRAM96 GB24 GB24 GB2 GB24 GB32 GB
Memory Bandwidth2,450 GB/s300 GB/s1,008 GB/s29 GB/s936 GB/s1,134 GB/s
TFLOPs (FP32)—30.382.60.76835.616.4
TFLOPs (FP16)—242————
TFLOPs432121165.20.7687116.4
TFLOPs (FP8)—485————
TDP600 W72 W450 W45 W350 W250 W
Launch DateMay 2022Mar 2023Oct 2022Jul 2014Sep 2020Nov 2019

Efficiency Metrics

MetricGaudi 2L4GeForce RTX 4090Quadro K620GeForce RTX 3090V100S
TFLOPs per Watt (FP32-eq)0.360.840.180.020.100.07
Memory Bandwidth per GB25.5 GB/s12.5 GB/s42.0 GB/s14.5 GB/s39.0 GB/s35.4 GB/s

Performance Equivalence

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

To match 1x Intel Habana Gaudi 2

NVIDIA L4
Compute (FP32-eq)
3.57x
Need 3.57x L4
VRAM
4.00x
Need 4.00x L4
Memory Bandwidth
8.17x
Need 8.17x L4
NVIDIA GeForce RTX 4090
Compute (FP32-eq)
2.62x
Need 2.62x GeForce RTX 4090
VRAM
4.00x
Need 4.00x GeForce RTX 4090
Memory Bandwidth
2.43x
Need 2.43x GeForce RTX 4090
NVIDIA Quadro K620
Compute (FP32-eq)
281.25x
Need 281.25x Quadro K620
VRAM
48.00x
Need 48.00x Quadro K620
Memory Bandwidth
84.48x
Need 84.48x Quadro K620
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
6.08x
Need 6.08x GeForce RTX 3090
VRAM
4.00x
Need 4.00x GeForce RTX 3090
Memory Bandwidth
2.62x
Need 2.62x GeForce RTX 3090
NVIDIA V100S
Compute (FP32-eq)
13.17x
Need 13.17x V100S
VRAM
3.00x
Need 3.00x V100S
Memory Bandwidth
2.16x
Need 2.16x V100S

To match 1x NVIDIA L4

Intel Habana Gaudi 2
Compute (FP32-eq)
0.28x
Gaudi 2 is 3.57x faster
VRAM
0.25x
Gaudi 2 has 4.00x more
Memory Bandwidth
0.12x
Gaudi 2 has 8.17x more
NVIDIA GeForce RTX 4090
Compute (FP32-eq)
0.73x
GeForce RTX 4090 is 1.37x faster
FP32 Compute
0.37x
GeForce RTX 4090 is 2.73x faster
VRAM
1.00x
GeForce RTX 4090 has 1.00x more
Memory Bandwidth
0.30x
GeForce RTX 4090 has 3.36x more
NVIDIA Quadro K620
Compute (FP32-eq)
78.78x
Need 78.78x Quadro K620
FP32 Compute
39.45x
Need 39.45x Quadro K620
VRAM
12.00x
Need 12.00x Quadro K620
Memory Bandwidth
10.34x
Need 10.34x Quadro K620
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
1.70x
Need 1.70x GeForce RTX 3090
FP32 Compute
0.85x
GeForce RTX 3090 is 1.17x faster
VRAM
1.00x
GeForce RTX 3090 has 1.00x more
Memory Bandwidth
0.32x
GeForce RTX 3090 has 3.12x more
NVIDIA V100S
Compute (FP32-eq)
3.69x
Need 3.69x V100S
FP32 Compute
1.85x
Need 1.85x V100S
VRAM
0.75x
V100S has 1.33x more
Memory Bandwidth
0.26x
V100S has 3.78x more

To match 1x NVIDIA GeForce RTX 4090

Intel Habana Gaudi 2
Compute (FP32-eq)
0.38x
Gaudi 2 is 2.62x faster
VRAM
0.25x
Gaudi 2 has 4.00x more
Memory Bandwidth
0.41x
Gaudi 2 has 2.43x more
NVIDIA L4
Compute (FP32-eq)
1.37x
Need 1.37x L4
FP32 Compute
2.73x
Need 2.73x L4
VRAM
1.00x
L4 has 1.00x more
Memory Bandwidth
3.36x
Need 3.36x L4
NVIDIA Quadro K620
Compute (FP32-eq)
107.55x
Need 107.55x Quadro K620
FP32 Compute
107.55x
Need 107.55x Quadro K620
VRAM
12.00x
Need 12.00x Quadro K620
Memory Bandwidth
34.76x
Need 34.76x Quadro K620
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
2.33x
Need 2.33x GeForce RTX 3090
FP32 Compute
2.32x
Need 2.32x GeForce RTX 3090
VRAM
1.00x
GeForce RTX 3090 has 1.00x more
Memory Bandwidth
1.08x
Need 1.08x GeForce RTX 3090
NVIDIA V100S
Compute (FP32-eq)
5.04x
Need 5.04x V100S
FP32 Compute
5.04x
Need 5.04x V100S
VRAM
0.75x
V100S has 1.33x more
Memory Bandwidth
0.89x
V100S has 1.13x more

To match 1x NVIDIA Quadro K620

Intel Habana Gaudi 2
Compute (FP32-eq)
0.00x
Gaudi 2 is 281.25x faster
VRAM
0.02x
Gaudi 2 has 48.00x more
Memory Bandwidth
0.01x
Gaudi 2 has 84.48x more
NVIDIA L4
Compute (FP32-eq)
0.01x
L4 is 78.78x faster
FP32 Compute
0.03x
L4 is 39.45x faster
VRAM
0.08x
L4 has 12.00x more
Memory Bandwidth
0.10x
L4 has 10.34x more
NVIDIA GeForce RTX 4090
Compute (FP32-eq)
0.01x
GeForce RTX 4090 is 107.55x faster
FP32 Compute
0.01x
GeForce RTX 4090 is 107.55x faster
VRAM
0.08x
GeForce RTX 4090 has 12.00x more
Memory Bandwidth
0.03x
GeForce RTX 4090 has 34.76x more
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.02x
GeForce RTX 3090 is 46.22x faster
FP32 Compute
0.02x
GeForce RTX 3090 is 46.35x faster
VRAM
0.08x
GeForce RTX 3090 has 12.00x more
Memory Bandwidth
0.03x
GeForce RTX 3090 has 32.28x more
NVIDIA V100S
Compute (FP32-eq)
0.05x
V100S is 21.35x faster
FP32 Compute
0.05x
V100S is 21.35x faster
VRAM
0.06x
V100S has 16.00x more
Memory Bandwidth
0.03x
V100S has 39.10x more

To match 1x NVIDIA GeForce RTX 3090

Intel Habana Gaudi 2
Compute (FP32-eq)
0.16x
Gaudi 2 is 6.08x faster
VRAM
0.25x
Gaudi 2 has 4.00x more
Memory Bandwidth
0.38x
Gaudi 2 has 2.62x more
NVIDIA L4
Compute (FP32-eq)
0.59x
L4 is 1.70x faster
FP32 Compute
1.17x
Need 1.17x L4
VRAM
1.00x
L4 has 1.00x more
Memory Bandwidth
3.12x
Need 3.12x L4
NVIDIA GeForce RTX 4090
Compute (FP32-eq)
0.43x
GeForce RTX 4090 is 2.33x faster
FP32 Compute
0.43x
GeForce RTX 4090 is 2.32x faster
VRAM
1.00x
GeForce RTX 4090 has 1.00x more
Memory Bandwidth
0.93x
GeForce RTX 4090 has 1.08x more
NVIDIA Quadro K620
Compute (FP32-eq)
46.22x
Need 46.22x Quadro K620
FP32 Compute
46.35x
Need 46.35x Quadro K620
VRAM
12.00x
Need 12.00x Quadro K620
Memory Bandwidth
32.28x
Need 32.28x Quadro K620
NVIDIA V100S
Compute (FP32-eq)
2.16x
Need 2.16x V100S
FP32 Compute
2.17x
Need 2.17x V100S
VRAM
0.75x
V100S has 1.33x more
Memory Bandwidth
0.83x
V100S has 1.21x more

To match 1x NVIDIA V100S

Intel Habana Gaudi 2
Compute (FP32-eq)
0.08x
Gaudi 2 is 13.17x faster
VRAM
0.33x
Gaudi 2 has 3.00x more
Memory Bandwidth
0.46x
Gaudi 2 has 2.16x more
NVIDIA L4
Compute (FP32-eq)
0.27x
L4 is 3.69x faster
FP32 Compute
0.54x
L4 is 1.85x faster
VRAM
1.33x
Need 1.33x L4
Memory Bandwidth
3.78x
Need 3.78x L4
NVIDIA GeForce RTX 4090
Compute (FP32-eq)
0.20x
GeForce RTX 4090 is 5.04x faster
FP32 Compute
0.20x
GeForce RTX 4090 is 5.04x faster
VRAM
1.33x
Need 1.33x GeForce RTX 4090
Memory Bandwidth
1.13x
Need 1.13x GeForce RTX 4090
NVIDIA Quadro K620
Compute (FP32-eq)
21.35x
Need 21.35x Quadro K620
FP32 Compute
21.35x
Need 21.35x Quadro K620
VRAM
16.00x
Need 16.00x Quadro K620
Memory Bandwidth
39.10x
Need 39.10x Quadro K620
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.46x
GeForce RTX 3090 is 2.16x faster
FP32 Compute
0.46x
GeForce RTX 3090 is 2.17x faster
VRAM
1.33x
Need 1.33x GeForce RTX 3090
Memory Bandwidth
1.21x
Need 1.21x GeForce RTX 3090

Pricing

Price TypeGaudi 2L4GeForce RTX 4090Quadro K620GeForce RTX 3090V100S
CAPEX (Street Price)—$4,000————
OPEX (per hour)—$0.80/hr$0.18/hr$0.05/hr$0.11/hr$0.88/hr
Price per TFLOPs (FP32-eq)—$66————