Compare XPUs

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

Select XPUs to Compare

Clear all (7)Jump to results
Showing 128 XPUs • 7 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 2Google TPU v5pNVIDIA GeForce RTX 5090NVIDIA Quadro K620NVIDIA Quadro P4000NVIDIA GeForce RTX 3090NVIDIA A100 SXM
ArchitectureGaudi Gen2TPU v5BlackwellKeplerPascalAmpereAmpere
Form FactorOAMMezzaninePCIePCIePCIePCIeSXM
VRAM96 GB95 GB32 GB2 GB8 GB24 GB80 GB
Memory Bandwidth2,450 GB/s—1,792 GB/s29 GB/s243 GB/s936 GB/s2,039 GB/s
TFLOPs (FP32)——920.7685.30435.619.5
TFLOPs (FP16)——————312
TFLOPs4324593180.7685.30471312
TFLOPs (FP8)———————
TDP600 W400 W575 W45 W105 W350 W400 W
Launch DateMay 2022Aug 2023Jan 2025Jul 2014Oct 2016Sep 2020May 2020

Efficiency Metrics

MetricGaudi 2TPU v5pGeForce RTX 5090Quadro K620Quadro P4000GeForce RTX 3090A100 SXM
TFLOPs per Watt (FP32-eq)0.360.570.280.020.050.100.39
Memory Bandwidth per GB25.5 GB/s—56.0 GB/s14.5 GB/s30.4 GB/s39.0 GB/s25.5 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

Google TPU v5p
Compute (FP32-eq)
0.94x
TPU v5p is 1.06x faster
VRAM
1.01x
Need 1.01x TPU v5p
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
1.36x
Need 1.36x GeForce RTX 5090
VRAM
3.00x
Need 3.00x GeForce RTX 5090
Memory Bandwidth
1.37x
Need 1.37x GeForce RTX 5090
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 Quadro P4000
Compute (FP32-eq)
40.72x
Need 40.72x Quadro P4000
VRAM
12.00x
Need 12.00x Quadro P4000
Memory Bandwidth
10.08x
Need 10.08x Quadro P4000
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 A100 SXM
Compute (FP32-eq)
1.38x
Need 1.38x A100 SXM
VRAM
1.20x
Need 1.20x A100 SXM
Memory Bandwidth
1.20x
Need 1.20x A100 SXM

To match 1x Google TPU v5p

Intel Habana Gaudi 2
Compute (FP32-eq)
1.06x
Need 1.06x Gaudi 2
VRAM
0.99x
Gaudi 2 has 1.01x more
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
1.44x
Need 1.44x GeForce RTX 5090
VRAM
2.97x
Need 2.97x GeForce RTX 5090
NVIDIA Quadro K620
Compute (FP32-eq)
298.83x
Need 298.83x Quadro K620
VRAM
47.50x
Need 47.50x Quadro K620
NVIDIA Quadro P4000
Compute (FP32-eq)
43.27x
Need 43.27x Quadro P4000
VRAM
11.88x
Need 11.88x Quadro P4000
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
6.46x
Need 6.46x GeForce RTX 3090
VRAM
3.96x
Need 3.96x GeForce RTX 3090
NVIDIA A100 SXM
Compute (FP32-eq)
1.47x
Need 1.47x A100 SXM
VRAM
1.19x
Need 1.19x A100 SXM

To match 1x NVIDIA GeForce RTX 5090

Intel Habana Gaudi 2
Compute (FP32-eq)
0.74x
Gaudi 2 is 1.36x faster
VRAM
0.33x
Gaudi 2 has 3.00x more
Memory Bandwidth
0.73x
Gaudi 2 has 1.37x more
Google TPU v5p
Compute (FP32-eq)
0.69x
TPU v5p is 1.44x faster
VRAM
0.34x
TPU v5p has 2.97x more
NVIDIA Quadro K620
Compute (FP32-eq)
207.03x
Need 207.03x Quadro K620
FP32 Compute
119.79x
Need 119.79x Quadro K620
VRAM
16.00x
Need 16.00x Quadro K620
Memory Bandwidth
61.79x
Need 61.79x Quadro K620
NVIDIA Quadro P4000
Compute (FP32-eq)
29.98x
Need 29.98x Quadro P4000
FP32 Compute
17.35x
Need 17.35x Quadro P4000
VRAM
4.00x
Need 4.00x Quadro P4000
Memory Bandwidth
7.37x
Need 7.37x Quadro P4000
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
4.48x
Need 4.48x GeForce RTX 3090
FP32 Compute
2.58x
Need 2.58x GeForce RTX 3090
VRAM
1.33x
Need 1.33x GeForce RTX 3090
Memory Bandwidth
1.91x
Need 1.91x GeForce RTX 3090
NVIDIA A100 SXM
Compute (FP32-eq)
1.02x
Need 1.02x A100 SXM
FP32 Compute
4.72x
Need 4.72x A100 SXM
VRAM
0.40x
A100 SXM has 2.50x more
Memory Bandwidth
0.88x
A100 SXM has 1.14x 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
Google TPU v5p
Compute (FP32-eq)
0.00x
TPU v5p is 298.83x faster
VRAM
0.02x
TPU v5p has 47.50x more
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
0.00x
GeForce RTX 5090 is 207.03x faster
FP32 Compute
0.01x
GeForce RTX 5090 is 119.79x faster
VRAM
0.06x
GeForce RTX 5090 has 16.00x more
Memory Bandwidth
0.02x
GeForce RTX 5090 has 61.79x more
NVIDIA Quadro P4000
Compute (FP32-eq)
0.14x
Quadro P4000 is 6.91x faster
FP32 Compute
0.14x
Quadro P4000 is 6.91x faster
VRAM
0.25x
Quadro P4000 has 4.00x more
Memory Bandwidth
0.12x
Quadro P4000 has 8.38x 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 A100 SXM
Compute (FP32-eq)
0.00x
A100 SXM is 203.13x faster
FP32 Compute
0.04x
A100 SXM is 25.39x faster
VRAM
0.03x
A100 SXM has 40.00x more
Memory Bandwidth
0.01x
A100 SXM has 70.31x more

To match 1x NVIDIA Quadro P4000

Intel Habana Gaudi 2
Compute (FP32-eq)
0.02x
Gaudi 2 is 40.72x faster
VRAM
0.08x
Gaudi 2 has 12.00x more
Memory Bandwidth
0.10x
Gaudi 2 has 10.08x more
Google TPU v5p
Compute (FP32-eq)
0.02x
TPU v5p is 43.27x faster
VRAM
0.08x
TPU v5p has 11.88x more
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
0.03x
GeForce RTX 5090 is 29.98x faster
FP32 Compute
0.06x
GeForce RTX 5090 is 17.35x faster
VRAM
0.25x
GeForce RTX 5090 has 4.00x more
Memory Bandwidth
0.14x
GeForce RTX 5090 has 7.37x more
NVIDIA Quadro K620
Compute (FP32-eq)
6.91x
Need 6.91x Quadro K620
FP32 Compute
6.91x
Need 6.91x Quadro K620
VRAM
4.00x
Need 4.00x Quadro K620
Memory Bandwidth
8.38x
Need 8.38x Quadro K620
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.15x
GeForce RTX 3090 is 6.69x faster
FP32 Compute
0.15x
GeForce RTX 3090 is 6.71x faster
VRAM
0.33x
GeForce RTX 3090 has 3.00x more
Memory Bandwidth
0.26x
GeForce RTX 3090 has 3.85x more
NVIDIA A100 SXM
Compute (FP32-eq)
0.03x
A100 SXM is 29.41x faster
FP32 Compute
0.27x
A100 SXM is 3.68x faster
VRAM
0.10x
A100 SXM has 10.00x more
Memory Bandwidth
0.12x
A100 SXM has 8.39x 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
Google TPU v5p
Compute (FP32-eq)
0.15x
TPU v5p is 6.46x faster
VRAM
0.25x
TPU v5p has 3.96x more
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
0.22x
GeForce RTX 5090 is 4.48x faster
FP32 Compute
0.39x
GeForce RTX 5090 is 2.58x faster
VRAM
0.75x
GeForce RTX 5090 has 1.33x more
Memory Bandwidth
0.52x
GeForce RTX 5090 has 1.91x 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 Quadro P4000
Compute (FP32-eq)
6.69x
Need 6.69x Quadro P4000
FP32 Compute
6.71x
Need 6.71x Quadro P4000
VRAM
3.00x
Need 3.00x Quadro P4000
Memory Bandwidth
3.85x
Need 3.85x Quadro P4000
NVIDIA A100 SXM
Compute (FP32-eq)
0.23x
A100 SXM is 4.39x faster
FP32 Compute
1.83x
Need 1.83x A100 SXM
VRAM
0.30x
A100 SXM has 3.33x more
Memory Bandwidth
0.46x
A100 SXM has 2.18x more

To match 1x NVIDIA A100 SXM

Intel Habana Gaudi 2
Compute (FP32-eq)
0.72x
Gaudi 2 is 1.38x faster
VRAM
0.83x
Gaudi 2 has 1.20x more
Memory Bandwidth
0.83x
Gaudi 2 has 1.20x more
Google TPU v5p
Compute (FP32-eq)
0.68x
TPU v5p is 1.47x faster
VRAM
0.84x
TPU v5p has 1.19x more
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
0.98x
GeForce RTX 5090 is 1.02x faster
FP32 Compute
0.21x
GeForce RTX 5090 is 4.72x faster
VRAM
2.50x
Need 2.50x GeForce RTX 5090
Memory Bandwidth
1.14x
Need 1.14x GeForce RTX 5090
NVIDIA Quadro K620
Compute (FP32-eq)
203.13x
Need 203.13x Quadro K620
FP32 Compute
25.39x
Need 25.39x Quadro K620
VRAM
40.00x
Need 40.00x Quadro K620
Memory Bandwidth
70.31x
Need 70.31x Quadro K620
NVIDIA Quadro P4000
Compute (FP32-eq)
29.41x
Need 29.41x Quadro P4000
FP32 Compute
3.68x
Need 3.68x Quadro P4000
VRAM
10.00x
Need 10.00x Quadro P4000
Memory Bandwidth
8.39x
Need 8.39x Quadro P4000
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
4.39x
Need 4.39x GeForce RTX 3090
FP32 Compute
0.55x
GeForce RTX 3090 is 1.83x faster
VRAM
3.33x
Need 3.33x GeForce RTX 3090
Memory Bandwidth
2.18x
Need 2.18x GeForce RTX 3090

Pricing

Price TypeGaudi 2TPU v5pGeForce RTX 5090Quadro K620Quadro P4000GeForce RTX 3090A100 SXM
CAPEX (Street Price)——————$15,000
OPEX (per hour)—$5.00/hr$0.27/hr$0.05/hr$0.51/hr$0.11/hr$4.05/hr
Price per TFLOPs (FP32-eq)——————$96