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

SpecificationMeta MTIA v1Google TPU v5eNVIDIA RTX 4000 SFF Ada GenerationNVIDIA GeForce RTX 4060NVIDIA P4NVIDIA T4GNVIDIA GeForce RTX 3090
ArchitectureMeta Training & Inference AcceleratorTPU v5Ada LovelaceAda LovelacePascalTuringAmpere
Form Factor—MezzaninePCIePCIePCIePCIePCIe
VRAM128 GB16 GB20 GB8 GB8 GB16 GB24 GB
Memory Bandwidth——360 GB/s272 GB/s192 GB/s320 GB/s936 GB/s
TFLOPs (FP32)——26.715.15.58.135.6
TFLOPs (FP16)———————
TFLOPs—19752305.56571
TFLOPs (FP8)———————
TDP400 W250 W70 W115 W75 W70 W350 W
Launch DateMay 2023Aug 2023Apr 2023Jun 2023Sep 2016May 2020Sep 2020

Efficiency Metrics

MetricMTIA v1TPU v5eRTX 4000 SFF Ada GenerationGeForce RTX 4060P4T4GGeForce RTX 3090
TFLOPs per Watt (FP32-eq)—0.390.370.130.070.460.10
Memory Bandwidth per GB——18.0 GB/s34.0 GB/s24.0 GB/s20.0 GB/s39.0 GB/s

Performance Equivalence

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

To match 1x Meta MTIA v1

Google TPU v5e
VRAM
8.00x
Need 8.00x TPU v5e
NVIDIA RTX 4000 SFF Ada Generation
VRAM
6.40x
Need 6.40x RTX 4000 SFF Ada Generation
NVIDIA GeForce RTX 4060
VRAM
16.00x
Need 16.00x GeForce RTX 4060
NVIDIA P4
VRAM
16.00x
Need 16.00x P4
NVIDIA T4G
VRAM
8.00x
Need 8.00x T4G
NVIDIA GeForce RTX 3090
VRAM
5.33x
Need 5.33x GeForce RTX 3090

To match 1x Google TPU v5e

Meta MTIA v1
VRAM
0.13x
MTIA v1 has 8.00x more
NVIDIA RTX 4000 SFF Ada Generation
Compute (FP32-eq)
3.79x
Need 3.79x RTX 4000 SFF Ada Generation
VRAM
0.80x
RTX 4000 SFF Ada Generation has 1.25x more
NVIDIA GeForce RTX 4060
Compute (FP32-eq)
6.57x
Need 6.57x GeForce RTX 4060
VRAM
2.00x
Need 2.00x GeForce RTX 4060
NVIDIA P4
Compute (FP32-eq)
17.91x
Need 17.91x P4
VRAM
2.00x
Need 2.00x P4
NVIDIA T4G
Compute (FP32-eq)
3.03x
Need 3.03x T4G
VRAM
1.00x
T4G has 1.00x more
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
2.77x
Need 2.77x GeForce RTX 3090
VRAM
0.67x
GeForce RTX 3090 has 1.50x more

To match 1x NVIDIA RTX 4000 SFF Ada Generation

Meta MTIA v1
VRAM
0.16x
MTIA v1 has 6.40x more
Google TPU v5e
Compute (FP32-eq)
0.26x
TPU v5e is 3.79x faster
VRAM
1.25x
Need 1.25x TPU v5e
NVIDIA GeForce RTX 4060
Compute (FP32-eq)
1.73x
Need 1.73x GeForce RTX 4060
FP32 Compute
1.77x
Need 1.77x GeForce RTX 4060
VRAM
2.50x
Need 2.50x GeForce RTX 4060
Memory Bandwidth
1.32x
Need 1.32x GeForce RTX 4060
NVIDIA P4
Compute (FP32-eq)
4.73x
Need 4.73x P4
FP32 Compute
4.85x
Need 4.85x P4
VRAM
2.50x
Need 2.50x P4
Memory Bandwidth
1.88x
Need 1.88x P4
NVIDIA T4G
Compute (FP32-eq)
0.80x
T4G is 1.25x faster
FP32 Compute
3.30x
Need 3.30x T4G
VRAM
1.25x
Need 1.25x T4G
Memory Bandwidth
1.13x
Need 1.13x T4G
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.73x
GeForce RTX 3090 is 1.37x faster
FP32 Compute
0.75x
GeForce RTX 3090 is 1.33x faster
VRAM
0.83x
GeForce RTX 3090 has 1.20x more
Memory Bandwidth
0.38x
GeForce RTX 3090 has 2.60x more

To match 1x NVIDIA GeForce RTX 4060

Meta MTIA v1
VRAM
0.06x
MTIA v1 has 16.00x more
Google TPU v5e
Compute (FP32-eq)
0.15x
TPU v5e is 6.57x faster
VRAM
0.50x
TPU v5e has 2.00x more
NVIDIA RTX 4000 SFF Ada Generation
Compute (FP32-eq)
0.58x
RTX 4000 SFF Ada Generation is 1.73x faster
FP32 Compute
0.57x
RTX 4000 SFF Ada Generation is 1.77x faster
VRAM
0.40x
RTX 4000 SFF Ada Generation has 2.50x more
Memory Bandwidth
0.76x
RTX 4000 SFF Ada Generation has 1.32x more
NVIDIA P4
Compute (FP32-eq)
2.73x
Need 2.73x P4
FP32 Compute
2.75x
Need 2.75x P4
VRAM
1.00x
P4 has 1.00x more
Memory Bandwidth
1.42x
Need 1.42x P4
NVIDIA T4G
Compute (FP32-eq)
0.46x
T4G is 2.17x faster
FP32 Compute
1.86x
Need 1.86x T4G
VRAM
0.50x
T4G has 2.00x more
Memory Bandwidth
0.85x
T4G has 1.18x more
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.42x
GeForce RTX 3090 is 2.37x faster
FP32 Compute
0.42x
GeForce RTX 3090 is 2.36x faster
VRAM
0.33x
GeForce RTX 3090 has 3.00x more
Memory Bandwidth
0.29x
GeForce RTX 3090 has 3.44x more

To match 1x NVIDIA P4

Meta MTIA v1
VRAM
0.06x
MTIA v1 has 16.00x more
Google TPU v5e
Compute (FP32-eq)
0.06x
TPU v5e is 17.91x faster
VRAM
0.50x
TPU v5e has 2.00x more
NVIDIA RTX 4000 SFF Ada Generation
Compute (FP32-eq)
0.21x
RTX 4000 SFF Ada Generation is 4.73x faster
FP32 Compute
0.21x
RTX 4000 SFF Ada Generation is 4.85x faster
VRAM
0.40x
RTX 4000 SFF Ada Generation has 2.50x more
Memory Bandwidth
0.53x
RTX 4000 SFF Ada Generation has 1.88x more
NVIDIA GeForce RTX 4060
Compute (FP32-eq)
0.37x
GeForce RTX 4060 is 2.73x faster
FP32 Compute
0.36x
GeForce RTX 4060 is 2.75x faster
VRAM
1.00x
GeForce RTX 4060 has 1.00x more
Memory Bandwidth
0.71x
GeForce RTX 4060 has 1.42x more
NVIDIA T4G
Compute (FP32-eq)
0.17x
T4G is 5.91x faster
FP32 Compute
0.68x
T4G is 1.47x faster
VRAM
0.50x
T4G has 2.00x more
Memory Bandwidth
0.60x
T4G has 1.67x more
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.15x
GeForce RTX 3090 is 6.45x faster
FP32 Compute
0.15x
GeForce RTX 3090 is 6.47x faster
VRAM
0.33x
GeForce RTX 3090 has 3.00x more
Memory Bandwidth
0.21x
GeForce RTX 3090 has 4.88x more

To match 1x NVIDIA T4G

Meta MTIA v1
VRAM
0.13x
MTIA v1 has 8.00x more
Google TPU v5e
Compute (FP32-eq)
0.33x
TPU v5e is 3.03x faster
VRAM
1.00x
TPU v5e has 1.00x more
NVIDIA RTX 4000 SFF Ada Generation
Compute (FP32-eq)
1.25x
Need 1.25x RTX 4000 SFF Ada Generation
FP32 Compute
0.30x
RTX 4000 SFF Ada Generation is 3.30x faster
VRAM
0.80x
RTX 4000 SFF Ada Generation has 1.25x more
Memory Bandwidth
0.89x
RTX 4000 SFF Ada Generation has 1.13x more
NVIDIA GeForce RTX 4060
Compute (FP32-eq)
2.17x
Need 2.17x GeForce RTX 4060
FP32 Compute
0.54x
GeForce RTX 4060 is 1.86x faster
VRAM
2.00x
Need 2.00x GeForce RTX 4060
Memory Bandwidth
1.18x
Need 1.18x GeForce RTX 4060
NVIDIA P4
Compute (FP32-eq)
5.91x
Need 5.91x P4
FP32 Compute
1.47x
Need 1.47x P4
VRAM
2.00x
Need 2.00x P4
Memory Bandwidth
1.67x
Need 1.67x P4
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.92x
GeForce RTX 3090 is 1.09x faster
FP32 Compute
0.23x
GeForce RTX 3090 is 4.40x faster
VRAM
0.67x
GeForce RTX 3090 has 1.50x more
Memory Bandwidth
0.34x
GeForce RTX 3090 has 2.92x more

To match 1x NVIDIA GeForce RTX 3090

Meta MTIA v1
VRAM
0.19x
MTIA v1 has 5.33x more
Google TPU v5e
Compute (FP32-eq)
0.36x
TPU v5e is 2.77x faster
VRAM
1.50x
Need 1.50x TPU v5e
NVIDIA RTX 4000 SFF Ada Generation
Compute (FP32-eq)
1.37x
Need 1.37x RTX 4000 SFF Ada Generation
FP32 Compute
1.33x
Need 1.33x RTX 4000 SFF Ada Generation
VRAM
1.20x
Need 1.20x RTX 4000 SFF Ada Generation
Memory Bandwidth
2.60x
Need 2.60x RTX 4000 SFF Ada Generation
NVIDIA GeForce RTX 4060
Compute (FP32-eq)
2.37x
Need 2.37x GeForce RTX 4060
FP32 Compute
2.36x
Need 2.36x GeForce RTX 4060
VRAM
3.00x
Need 3.00x GeForce RTX 4060
Memory Bandwidth
3.44x
Need 3.44x GeForce RTX 4060
NVIDIA P4
Compute (FP32-eq)
6.45x
Need 6.45x P4
FP32 Compute
6.47x
Need 6.47x P4
VRAM
3.00x
Need 3.00x P4
Memory Bandwidth
4.88x
Need 4.88x P4
NVIDIA T4G
Compute (FP32-eq)
1.09x
Need 1.09x T4G
FP32 Compute
4.40x
Need 4.40x T4G
VRAM
1.50x
Need 1.50x T4G
Memory Bandwidth
2.92x
Need 2.92x T4G

Pricing

Price TypeMTIA v1TPU v5eRTX 4000 SFF Ada GenerationGeForce RTX 4060P4T4GGeForce RTX 3090
CAPEX (Street Price)———————
OPEX (per hour)—$1.80/hr$0.15/hr$0.06/hr$0.04/hr$0.42/hr$0.11/hr
Price per TFLOPs (FP32-eq)———————