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

SpecificationAMD MI300XGoogle TPU v4NVIDIA GeForce RTX 4070 SuperNVIDIA GeForce GTX 1660NVIDIA RTX A4000NVIDIA GeForce RTX 3090NVIDIA GeForce GTX 1080
ArchitectureCDNA 3TPU v4Ada LovelaceTuringAmpereAmperePascal
Form FactorOAMMezzaninePCIePCIePCIePCIePCIe
VRAM192 GB32 GB12 GB6 GB16 GB24 GB8 GB
Memory Bandwidth5,300 GB/s—504 GB/s192 GB/s448 GB/s936 GB/s320 GB/s
TFLOPs (FP32)163.4——5.02719.235.68.873
TFLOPs (FP16)1,307——————
TFLOPs1,307275705.02738.7718.873
TFLOPs (FP8)2,614——————
TDP750 W300 W220 W120 W140 W350 W180 W
Launch DateDec 2023May 2021Jan 2024Mar 2019Apr 2021Sep 2020May 2016

Efficiency Metrics

MetricMI300XTPU v4GeForce RTX 4070 SuperGeForce GTX 1660RTX A4000GeForce RTX 3090GeForce GTX 1080
TFLOPs per Watt (FP32-eq)0.870.460.160.040.140.100.05
Memory Bandwidth per GB27.6 GB/s—42.0 GB/s32.0 GB/s28.0 GB/s39.0 GB/s40.0 GB/s

Performance Equivalence

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

To match 1x AMD MI300X

Google TPU v4
Compute (FP32-eq)
4.75x
Need 4.75x TPU v4
VRAM
6.00x
Need 6.00x TPU v4
NVIDIA GeForce RTX 4070 Super
Compute (FP32-eq)
18.67x
Need 18.67x GeForce RTX 4070 Super
VRAM
16.00x
Need 16.00x GeForce RTX 4070 Super
Memory Bandwidth
10.52x
Need 10.52x GeForce RTX 4070 Super
NVIDIA GeForce GTX 1660
Compute (FP32-eq)
130.00x
Need 130.00x GeForce GTX 1660
FP32 Compute
32.50x
Need 32.50x GeForce GTX 1660
VRAM
32.00x
Need 32.00x GeForce GTX 1660
Memory Bandwidth
27.60x
Need 27.60x GeForce GTX 1660
NVIDIA RTX A4000
Compute (FP32-eq)
33.77x
Need 33.77x RTX A4000
FP32 Compute
8.51x
Need 8.51x RTX A4000
VRAM
12.00x
Need 12.00x RTX A4000
Memory Bandwidth
11.83x
Need 11.83x RTX A4000
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
18.41x
Need 18.41x GeForce RTX 3090
FP32 Compute
4.59x
Need 4.59x GeForce RTX 3090
VRAM
8.00x
Need 8.00x GeForce RTX 3090
Memory Bandwidth
5.66x
Need 5.66x GeForce RTX 3090
NVIDIA GeForce GTX 1080
Compute (FP32-eq)
73.65x
Need 73.65x GeForce GTX 1080
FP32 Compute
18.42x
Need 18.42x GeForce GTX 1080
VRAM
24.00x
Need 24.00x GeForce GTX 1080
Memory Bandwidth
16.56x
Need 16.56x GeForce GTX 1080

To match 1x Google TPU v4

AMD MI300X
Compute (FP32-eq)
0.21x
MI300X is 4.75x faster
VRAM
0.17x
MI300X has 6.00x more
NVIDIA GeForce RTX 4070 Super
Compute (FP32-eq)
3.93x
Need 3.93x GeForce RTX 4070 Super
VRAM
2.67x
Need 2.67x GeForce RTX 4070 Super
NVIDIA GeForce GTX 1660
Compute (FP32-eq)
27.35x
Need 27.35x GeForce GTX 1660
VRAM
5.33x
Need 5.33x GeForce GTX 1660
NVIDIA RTX A4000
Compute (FP32-eq)
7.11x
Need 7.11x RTX A4000
VRAM
2.00x
Need 2.00x RTX A4000
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
3.87x
Need 3.87x GeForce RTX 3090
VRAM
1.33x
Need 1.33x GeForce RTX 3090
NVIDIA GeForce GTX 1080
Compute (FP32-eq)
15.50x
Need 15.50x GeForce GTX 1080
VRAM
4.00x
Need 4.00x GeForce GTX 1080

To match 1x NVIDIA GeForce RTX 4070 Super

AMD MI300X
Compute (FP32-eq)
0.05x
MI300X is 18.67x faster
VRAM
0.06x
MI300X has 16.00x more
Memory Bandwidth
0.10x
MI300X has 10.52x more
Google TPU v4
Compute (FP32-eq)
0.25x
TPU v4 is 3.93x faster
VRAM
0.38x
TPU v4 has 2.67x more
NVIDIA GeForce GTX 1660
Compute (FP32-eq)
6.96x
Need 6.96x GeForce GTX 1660
VRAM
2.00x
Need 2.00x GeForce GTX 1660
Memory Bandwidth
2.63x
Need 2.63x GeForce GTX 1660
NVIDIA RTX A4000
Compute (FP32-eq)
1.81x
Need 1.81x RTX A4000
VRAM
0.75x
RTX A4000 has 1.33x more
Memory Bandwidth
1.13x
Need 1.13x RTX A4000
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.99x
GeForce RTX 3090 is 1.01x faster
VRAM
0.50x
GeForce RTX 3090 has 2.00x more
Memory Bandwidth
0.54x
GeForce RTX 3090 has 1.86x more
NVIDIA GeForce GTX 1080
Compute (FP32-eq)
3.94x
Need 3.94x GeForce GTX 1080
VRAM
1.50x
Need 1.50x GeForce GTX 1080
Memory Bandwidth
1.57x
Need 1.57x GeForce GTX 1080

To match 1x NVIDIA GeForce GTX 1660

AMD MI300X
Compute (FP32-eq)
0.01x
MI300X is 130.00x faster
FP32 Compute
0.03x
MI300X is 32.50x faster
VRAM
0.03x
MI300X has 32.00x more
Memory Bandwidth
0.04x
MI300X has 27.60x more
Google TPU v4
Compute (FP32-eq)
0.04x
TPU v4 is 27.35x faster
VRAM
0.19x
TPU v4 has 5.33x more
NVIDIA GeForce RTX 4070 Super
Compute (FP32-eq)
0.14x
GeForce RTX 4070 Super is 6.96x faster
VRAM
0.50x
GeForce RTX 4070 Super has 2.00x more
Memory Bandwidth
0.38x
GeForce RTX 4070 Super has 2.63x more
NVIDIA RTX A4000
Compute (FP32-eq)
0.26x
RTX A4000 is 3.85x faster
FP32 Compute
0.26x
RTX A4000 is 3.82x faster
VRAM
0.38x
RTX A4000 has 2.67x more
Memory Bandwidth
0.43x
RTX A4000 has 2.33x more
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.14x
GeForce RTX 3090 is 7.06x faster
FP32 Compute
0.14x
GeForce RTX 3090 is 7.08x faster
VRAM
0.25x
GeForce RTX 3090 has 4.00x more
Memory Bandwidth
0.21x
GeForce RTX 3090 has 4.88x more
NVIDIA GeForce GTX 1080
Compute (FP32-eq)
0.57x
GeForce GTX 1080 is 1.77x faster
FP32 Compute
0.57x
GeForce GTX 1080 is 1.77x faster
VRAM
0.75x
GeForce GTX 1080 has 1.33x more
Memory Bandwidth
0.60x
GeForce GTX 1080 has 1.67x more

To match 1x NVIDIA RTX A4000

AMD MI300X
Compute (FP32-eq)
0.03x
MI300X is 33.77x faster
FP32 Compute
0.12x
MI300X is 8.51x faster
VRAM
0.08x
MI300X has 12.00x more
Memory Bandwidth
0.08x
MI300X has 11.83x more
Google TPU v4
Compute (FP32-eq)
0.14x
TPU v4 is 7.11x faster
VRAM
0.50x
TPU v4 has 2.00x more
NVIDIA GeForce RTX 4070 Super
Compute (FP32-eq)
0.55x
GeForce RTX 4070 Super is 1.81x faster
VRAM
1.33x
Need 1.33x GeForce RTX 4070 Super
Memory Bandwidth
0.89x
GeForce RTX 4070 Super has 1.13x more
NVIDIA GeForce GTX 1660
Compute (FP32-eq)
3.85x
Need 3.85x GeForce GTX 1660
FP32 Compute
3.82x
Need 3.82x GeForce GTX 1660
VRAM
2.67x
Need 2.67x GeForce GTX 1660
Memory Bandwidth
2.33x
Need 2.33x GeForce GTX 1660
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.55x
GeForce RTX 3090 is 1.83x faster
FP32 Compute
0.54x
GeForce RTX 3090 is 1.85x faster
VRAM
0.67x
GeForce RTX 3090 has 1.50x more
Memory Bandwidth
0.48x
GeForce RTX 3090 has 2.09x more
NVIDIA GeForce GTX 1080
Compute (FP32-eq)
2.18x
Need 2.18x GeForce GTX 1080
FP32 Compute
2.16x
Need 2.16x GeForce GTX 1080
VRAM
2.00x
Need 2.00x GeForce GTX 1080
Memory Bandwidth
1.40x
Need 1.40x GeForce GTX 1080

To match 1x NVIDIA GeForce RTX 3090

AMD MI300X
Compute (FP32-eq)
0.05x
MI300X is 18.41x faster
FP32 Compute
0.22x
MI300X is 4.59x faster
VRAM
0.13x
MI300X has 8.00x more
Memory Bandwidth
0.18x
MI300X has 5.66x more
Google TPU v4
Compute (FP32-eq)
0.26x
TPU v4 is 3.87x faster
VRAM
0.75x
TPU v4 has 1.33x more
NVIDIA GeForce RTX 4070 Super
Compute (FP32-eq)
1.01x
Need 1.01x GeForce RTX 4070 Super
VRAM
2.00x
Need 2.00x GeForce RTX 4070 Super
Memory Bandwidth
1.86x
Need 1.86x GeForce RTX 4070 Super
NVIDIA GeForce GTX 1660
Compute (FP32-eq)
7.06x
Need 7.06x GeForce GTX 1660
FP32 Compute
7.08x
Need 7.08x GeForce GTX 1660
VRAM
4.00x
Need 4.00x GeForce GTX 1660
Memory Bandwidth
4.88x
Need 4.88x GeForce GTX 1660
NVIDIA RTX A4000
Compute (FP32-eq)
1.83x
Need 1.83x RTX A4000
FP32 Compute
1.85x
Need 1.85x RTX A4000
VRAM
1.50x
Need 1.50x RTX A4000
Memory Bandwidth
2.09x
Need 2.09x RTX A4000
NVIDIA GeForce GTX 1080
Compute (FP32-eq)
4.00x
Need 4.00x GeForce GTX 1080
FP32 Compute
4.01x
Need 4.01x GeForce GTX 1080
VRAM
3.00x
Need 3.00x GeForce GTX 1080
Memory Bandwidth
2.92x
Need 2.92x GeForce GTX 1080

To match 1x NVIDIA GeForce GTX 1080

AMD MI300X
Compute (FP32-eq)
0.01x
MI300X is 73.65x faster
FP32 Compute
0.05x
MI300X is 18.42x faster
VRAM
0.04x
MI300X has 24.00x more
Memory Bandwidth
0.06x
MI300X has 16.56x more
Google TPU v4
Compute (FP32-eq)
0.06x
TPU v4 is 15.50x faster
VRAM
0.25x
TPU v4 has 4.00x more
NVIDIA GeForce RTX 4070 Super
Compute (FP32-eq)
0.25x
GeForce RTX 4070 Super is 3.94x faster
VRAM
0.67x
GeForce RTX 4070 Super has 1.50x more
Memory Bandwidth
0.63x
GeForce RTX 4070 Super has 1.58x more
NVIDIA GeForce GTX 1660
Compute (FP32-eq)
1.77x
Need 1.77x GeForce GTX 1660
FP32 Compute
1.77x
Need 1.77x GeForce GTX 1660
VRAM
1.33x
Need 1.33x GeForce GTX 1660
Memory Bandwidth
1.67x
Need 1.67x GeForce GTX 1660
NVIDIA RTX A4000
Compute (FP32-eq)
0.46x
RTX A4000 is 2.18x faster
FP32 Compute
0.46x
RTX A4000 is 2.16x faster
VRAM
0.50x
RTX A4000 has 2.00x more
Memory Bandwidth
0.71x
RTX A4000 has 1.40x more
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.25x
GeForce RTX 3090 is 4.00x faster
FP32 Compute
0.25x
GeForce RTX 3090 is 4.01x faster
VRAM
0.33x
GeForce RTX 3090 has 3.00x more
Memory Bandwidth
0.34x
GeForce RTX 3090 has 2.92x more

Pricing

Price TypeMI300XTPU v4GeForce RTX 4070 SuperGeForce GTX 1660RTX A4000GeForce RTX 3090GeForce GTX 1080
CAPEX (Street Price)$35,000——————
OPEX (per hour)$10.40/hr$3.00/hr—$0.04/hr$0.11/hr$0.11/hr$0.04/hr
Price per TFLOPs (FP32-eq)$54——————