Compare XPUs

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

Select XPUs to Compare

Showing 128 XPUs6 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

SpecificationNVIDIA RTX 4500 Ada GenerationNVIDIA B100NVIDIA GeForce RTX 4060 TiNVIDIA GeForce GTX 1650NVIDIA GeForce RTX 3090NVIDIA L40
ArchitectureAda LovelaceBlackwellAda LovelaceTuringAmpereAda Lovelace
Form FactorPCIeSXMPCIePCIePCIePCIe
VRAM24 GB192 GB8 GB4 GB24 GB48 GB
Memory Bandwidth576 GB/s8,000 GB/s288 GB/s128 GB/s936 GB/s864 GB/s
TFLOPs (FP32)48.54522.12.98435.645
TFLOPs (FP16)
TFLOPs971,800442.98471181.05
TFLOPs (FP8)
TDP210 W700 W160 W75 W350 W300 W
Launch DateMar 2023Mar 2024May 2023Apr 2019Sep 2020Oct 2022

Efficiency Metrics

MetricRTX 4500 Ada GenerationB100GeForce RTX 4060 TiGeForce GTX 1650GeForce RTX 3090L40
TFLOPs per Watt (FP32-eq)0.231.290.140.040.100.30
Memory Bandwidth per GB24.0 GB/s41.7 GB/s36.0 GB/s32.0 GB/s39.0 GB/s18.0 GB/s

Performance Equivalence

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

To match 1x NVIDIA RTX 4500 Ada Generation

NVIDIA B100
Compute (FP32-eq)
0.05x
B100 is 18.56x faster
FP32 Compute
1.08x
Need 1.08x B100
VRAM
0.13x
B100 has 8.00x more
Memory Bandwidth
0.07x
B100 has 13.89x more
NVIDIA GeForce RTX 4060 Ti
Compute (FP32-eq)
2.20x
Need 2.20x GeForce RTX 4060 Ti
FP32 Compute
2.19x
Need 2.19x GeForce RTX 4060 Ti
VRAM
3.00x
Need 3.00x GeForce RTX 4060 Ti
Memory Bandwidth
2.00x
Need 2.00x GeForce RTX 4060 Ti
NVIDIA GeForce GTX 1650
Compute (FP32-eq)
16.25x
Need 16.25x GeForce GTX 1650
FP32 Compute
16.25x
Need 16.25x GeForce GTX 1650
VRAM
6.00x
Need 6.00x GeForce GTX 1650
Memory Bandwidth
4.50x
Need 4.50x GeForce GTX 1650
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
1.37x
Need 1.37x GeForce RTX 3090
FP32 Compute
1.36x
Need 1.36x GeForce RTX 3090
VRAM
1.00x
GeForce RTX 3090 has 1.00x more
Memory Bandwidth
0.62x
GeForce RTX 3090 has 1.63x more
NVIDIA L40
Compute (FP32-eq)
0.54x
L40 is 1.87x faster
FP32 Compute
1.08x
Need 1.08x L40
VRAM
0.50x
L40 has 2.00x more
Memory Bandwidth
0.67x
L40 has 1.50x more

To match 1x NVIDIA B100

NVIDIA RTX 4500 Ada Generation
Compute (FP32-eq)
18.56x
Need 18.56x RTX 4500 Ada Generation
FP32 Compute
0.93x
RTX 4500 Ada Generation is 1.08x faster
VRAM
8.00x
Need 8.00x RTX 4500 Ada Generation
Memory Bandwidth
13.89x
Need 13.89x RTX 4500 Ada Generation
NVIDIA GeForce RTX 4060 Ti
Compute (FP32-eq)
40.91x
Need 40.91x GeForce RTX 4060 Ti
FP32 Compute
2.04x
Need 2.04x GeForce RTX 4060 Ti
VRAM
24.00x
Need 24.00x GeForce RTX 4060 Ti
Memory Bandwidth
27.78x
Need 27.78x GeForce RTX 4060 Ti
NVIDIA GeForce GTX 1650
Compute (FP32-eq)
301.61x
Need 301.61x GeForce GTX 1650
FP32 Compute
15.08x
Need 15.08x GeForce GTX 1650
VRAM
48.00x
Need 48.00x GeForce GTX 1650
Memory Bandwidth
62.50x
Need 62.50x GeForce GTX 1650
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
25.35x
Need 25.35x GeForce RTX 3090
FP32 Compute
1.26x
Need 1.26x GeForce RTX 3090
VRAM
8.00x
Need 8.00x GeForce RTX 3090
Memory Bandwidth
8.55x
Need 8.55x GeForce RTX 3090
NVIDIA L40
Compute (FP32-eq)
9.94x
Need 9.94x L40
FP32 Compute
1.00x
L40 is 1.00x faster
VRAM
4.00x
Need 4.00x L40
Memory Bandwidth
9.26x
Need 9.26x L40

To match 1x NVIDIA GeForce RTX 4060 Ti

NVIDIA RTX 4500 Ada Generation
Compute (FP32-eq)
0.45x
RTX 4500 Ada Generation is 2.20x faster
FP32 Compute
0.46x
RTX 4500 Ada Generation is 2.19x faster
VRAM
0.33x
RTX 4500 Ada Generation has 3.00x more
Memory Bandwidth
0.50x
RTX 4500 Ada Generation has 2.00x more
NVIDIA B100
Compute (FP32-eq)
0.02x
B100 is 40.91x faster
FP32 Compute
0.49x
B100 is 2.04x faster
VRAM
0.04x
B100 has 24.00x more
Memory Bandwidth
0.04x
B100 has 27.78x more
NVIDIA GeForce GTX 1650
Compute (FP32-eq)
7.37x
Need 7.37x GeForce GTX 1650
FP32 Compute
7.41x
Need 7.41x GeForce GTX 1650
VRAM
2.00x
Need 2.00x GeForce GTX 1650
Memory Bandwidth
2.25x
Need 2.25x GeForce GTX 1650
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.62x
GeForce RTX 3090 is 1.61x faster
FP32 Compute
0.62x
GeForce RTX 3090 is 1.61x faster
VRAM
0.33x
GeForce RTX 3090 has 3.00x more
Memory Bandwidth
0.31x
GeForce RTX 3090 has 3.25x more
NVIDIA L40
Compute (FP32-eq)
0.24x
L40 is 4.11x faster
FP32 Compute
0.49x
L40 is 2.04x faster
VRAM
0.17x
L40 has 6.00x more
Memory Bandwidth
0.33x
L40 has 3.00x more

To match 1x NVIDIA GeForce GTX 1650

NVIDIA RTX 4500 Ada Generation
Compute (FP32-eq)
0.06x
RTX 4500 Ada Generation is 16.25x faster
FP32 Compute
0.06x
RTX 4500 Ada Generation is 16.25x faster
VRAM
0.17x
RTX 4500 Ada Generation has 6.00x more
Memory Bandwidth
0.22x
RTX 4500 Ada Generation has 4.50x more
NVIDIA B100
Compute (FP32-eq)
0.00x
B100 is 301.61x faster
FP32 Compute
0.07x
B100 is 15.08x faster
VRAM
0.02x
B100 has 48.00x more
Memory Bandwidth
0.02x
B100 has 62.50x more
NVIDIA GeForce RTX 4060 Ti
Compute (FP32-eq)
0.14x
GeForce RTX 4060 Ti is 7.37x faster
FP32 Compute
0.14x
GeForce RTX 4060 Ti is 7.41x faster
VRAM
0.50x
GeForce RTX 4060 Ti has 2.00x more
Memory Bandwidth
0.44x
GeForce RTX 4060 Ti has 2.25x more
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.08x
GeForce RTX 3090 is 11.90x faster
FP32 Compute
0.08x
GeForce RTX 3090 is 11.93x faster
VRAM
0.17x
GeForce RTX 3090 has 6.00x more
Memory Bandwidth
0.14x
GeForce RTX 3090 has 7.31x more
NVIDIA L40
Compute (FP32-eq)
0.03x
L40 is 30.34x faster
FP32 Compute
0.07x
L40 is 15.08x faster
VRAM
0.08x
L40 has 12.00x more
Memory Bandwidth
0.15x
L40 has 6.75x more

To match 1x NVIDIA GeForce RTX 3090

NVIDIA RTX 4500 Ada Generation
Compute (FP32-eq)
0.73x
RTX 4500 Ada Generation is 1.37x faster
FP32 Compute
0.73x
RTX 4500 Ada Generation is 1.36x faster
VRAM
1.00x
RTX 4500 Ada Generation has 1.00x more
Memory Bandwidth
1.63x
Need 1.63x RTX 4500 Ada Generation
NVIDIA B100
Compute (FP32-eq)
0.04x
B100 is 25.35x faster
FP32 Compute
0.79x
B100 is 1.26x faster
VRAM
0.13x
B100 has 8.00x more
Memory Bandwidth
0.12x
B100 has 8.55x more
NVIDIA GeForce RTX 4060 Ti
Compute (FP32-eq)
1.61x
Need 1.61x GeForce RTX 4060 Ti
FP32 Compute
1.61x
Need 1.61x GeForce RTX 4060 Ti
VRAM
3.00x
Need 3.00x GeForce RTX 4060 Ti
Memory Bandwidth
3.25x
Need 3.25x GeForce RTX 4060 Ti
NVIDIA GeForce GTX 1650
Compute (FP32-eq)
11.90x
Need 11.90x GeForce GTX 1650
FP32 Compute
11.93x
Need 11.93x GeForce GTX 1650
VRAM
6.00x
Need 6.00x GeForce GTX 1650
Memory Bandwidth
7.31x
Need 7.31x GeForce GTX 1650
NVIDIA L40
Compute (FP32-eq)
0.39x
L40 is 2.55x faster
FP32 Compute
0.79x
L40 is 1.26x faster
VRAM
0.50x
L40 has 2.00x more
Memory Bandwidth
1.08x
Need 1.08x L40

To match 1x NVIDIA L40

NVIDIA RTX 4500 Ada Generation
Compute (FP32-eq)
1.87x
Need 1.87x RTX 4500 Ada Generation
FP32 Compute
0.93x
RTX 4500 Ada Generation is 1.08x faster
VRAM
2.00x
Need 2.00x RTX 4500 Ada Generation
Memory Bandwidth
1.50x
Need 1.50x RTX 4500 Ada Generation
NVIDIA B100
Compute (FP32-eq)
0.10x
B100 is 9.94x faster
FP32 Compute
1.00x
B100 is 1.00x faster
VRAM
0.25x
B100 has 4.00x more
Memory Bandwidth
0.11x
B100 has 9.26x more
NVIDIA GeForce RTX 4060 Ti
Compute (FP32-eq)
4.11x
Need 4.11x GeForce RTX 4060 Ti
FP32 Compute
2.04x
Need 2.04x GeForce RTX 4060 Ti
VRAM
6.00x
Need 6.00x GeForce RTX 4060 Ti
Memory Bandwidth
3.00x
Need 3.00x GeForce RTX 4060 Ti
NVIDIA GeForce GTX 1650
Compute (FP32-eq)
30.34x
Need 30.34x GeForce GTX 1650
FP32 Compute
15.08x
Need 15.08x GeForce GTX 1650
VRAM
12.00x
Need 12.00x GeForce GTX 1650
Memory Bandwidth
6.75x
Need 6.75x GeForce GTX 1650
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
2.55x
Need 2.55x GeForce RTX 3090
FP32 Compute
1.26x
Need 1.26x GeForce RTX 3090
VRAM
2.00x
Need 2.00x GeForce RTX 3090
Memory Bandwidth
0.92x
GeForce RTX 3090 has 1.08x more

Pricing

Price TypeRTX 4500 Ada GenerationB100GeForce RTX 4060 TiGeForce GTX 1650GeForce RTX 3090L40
CAPEX (Street Price)
OPEX (per hour)$0.10/hr$0.04/hr$0.11/hr$0.69/hr
Price per TFLOPs (FP32-eq)