Compare XPUs

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

Select XPUs to Compare

Clear all (8)Jump to results
Showing 128 XPUs • 8 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

SpecificationCerebras WSE-3Tenstorrent WormholeNVIDIA RTX 6000 BlackwellNVIDIA GeForce RTX 5070NVIDIA RTX 5880 Ada GenerationNVIDIA T4GNVIDIA GeForce GTX 1070NVIDIA GeForce RTX 3090
ArchitectureWafer Scale EngineTensix CoreBlackwellBlackwellAda LovelaceTuringPascalAmpere
Form Factor——PCIePCIePCIePCIePCIePCIe
VRAM44 GB24 GB96 GB12 GB48 GB16 GB8 GB24 GB
Memory Bandwidth——1,536 GB/s672 GB/s960 GB/s320 GB/s256 GB/s936 GB/s
TFLOPs (FP32)——1813483.58.16.46335.6
TFLOPs (FP16)————————
TFLOPs—364362110167656.46371
TFLOPs (FP8)————————
TDP23000 W160 W300 W250 W250 W70 W150 W350 W
Launch DateMar 2024Oct 2023Jan 2025Feb 2025Mar 2024May 2020Jun 2016Sep 2020

Efficiency Metrics

MetricWSE-3WormholeRTX 6000 BlackwellGeForce RTX 5070RTX 5880 Ada GenerationT4GGeForce GTX 1070GeForce RTX 3090
TFLOPs per Watt (FP32-eq)—1.140.600.220.330.460.040.10
Memory Bandwidth per GB——16.0 GB/s56.0 GB/s20.0 GB/s20.0 GB/s32.0 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 Cerebras WSE-3

Tenstorrent Wormhole
VRAM
1.83x
Need 1.83x Wormhole
NVIDIA RTX 6000 Blackwell
VRAM
0.46x
RTX 6000 Blackwell has 2.18x more
NVIDIA GeForce RTX 5070
VRAM
3.67x
Need 3.67x GeForce RTX 5070
NVIDIA RTX 5880 Ada Generation
VRAM
0.92x
RTX 5880 Ada Generation has 1.09x more
NVIDIA T4G
VRAM
2.75x
Need 2.75x T4G
NVIDIA GeForce GTX 1070
VRAM
5.50x
Need 5.50x GeForce GTX 1070
NVIDIA GeForce RTX 3090
VRAM
1.83x
Need 1.83x GeForce RTX 3090

To match 1x Tenstorrent Wormhole

Cerebras WSE-3
VRAM
0.55x
WSE-3 has 1.83x more
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
1.01x
Need 1.01x RTX 6000 Blackwell
VRAM
0.25x
RTX 6000 Blackwell has 4.00x more
NVIDIA GeForce RTX 5070
Compute (FP32-eq)
3.31x
Need 3.31x GeForce RTX 5070
VRAM
2.00x
Need 2.00x GeForce RTX 5070
NVIDIA RTX 5880 Ada Generation
Compute (FP32-eq)
2.18x
Need 2.18x RTX 5880 Ada Generation
VRAM
0.50x
RTX 5880 Ada Generation has 2.00x more
NVIDIA T4G
Compute (FP32-eq)
5.60x
Need 5.60x T4G
VRAM
1.50x
Need 1.50x T4G
NVIDIA GeForce GTX 1070
Compute (FP32-eq)
28.16x
Need 28.16x GeForce GTX 1070
VRAM
3.00x
Need 3.00x GeForce GTX 1070
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
5.13x
Need 5.13x GeForce RTX 3090
VRAM
1.00x
GeForce RTX 3090 has 1.00x more

To match 1x NVIDIA RTX 6000 Blackwell

Cerebras WSE-3
VRAM
2.18x
Need 2.18x WSE-3
Tenstorrent Wormhole
Compute (FP32-eq)
0.99x
Wormhole is 1.01x faster
VRAM
4.00x
Need 4.00x Wormhole
NVIDIA GeForce RTX 5070
Compute (FP32-eq)
3.29x
Need 3.29x GeForce RTX 5070
FP32 Compute
5.32x
Need 5.32x GeForce RTX 5070
VRAM
8.00x
Need 8.00x GeForce RTX 5070
Memory Bandwidth
2.29x
Need 2.29x GeForce RTX 5070
NVIDIA RTX 5880 Ada Generation
Compute (FP32-eq)
2.17x
Need 2.17x RTX 5880 Ada Generation
FP32 Compute
2.17x
Need 2.17x RTX 5880 Ada Generation
VRAM
2.00x
Need 2.00x RTX 5880 Ada Generation
Memory Bandwidth
1.60x
Need 1.60x RTX 5880 Ada Generation
NVIDIA T4G
Compute (FP32-eq)
5.57x
Need 5.57x T4G
FP32 Compute
22.35x
Need 22.35x T4G
VRAM
6.00x
Need 6.00x T4G
Memory Bandwidth
4.80x
Need 4.80x T4G
NVIDIA GeForce GTX 1070
Compute (FP32-eq)
28.01x
Need 28.01x GeForce GTX 1070
FP32 Compute
28.01x
Need 28.01x GeForce GTX 1070
VRAM
12.00x
Need 12.00x GeForce GTX 1070
Memory Bandwidth
6.00x
Need 6.00x GeForce GTX 1070
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
5.10x
Need 5.10x GeForce RTX 3090
FP32 Compute
5.08x
Need 5.08x GeForce RTX 3090
VRAM
4.00x
Need 4.00x GeForce RTX 3090
Memory Bandwidth
1.64x
Need 1.64x GeForce RTX 3090

To match 1x NVIDIA GeForce RTX 5070

Cerebras WSE-3
VRAM
0.27x
WSE-3 has 3.67x more
Tenstorrent Wormhole
Compute (FP32-eq)
0.30x
Wormhole is 3.31x faster
VRAM
0.50x
Wormhole has 2.00x more
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
0.30x
RTX 6000 Blackwell is 3.29x faster
FP32 Compute
0.19x
RTX 6000 Blackwell is 5.32x faster
VRAM
0.13x
RTX 6000 Blackwell has 8.00x more
Memory Bandwidth
0.44x
RTX 6000 Blackwell has 2.29x more
NVIDIA RTX 5880 Ada Generation
Compute (FP32-eq)
0.66x
RTX 5880 Ada Generation is 1.52x faster
FP32 Compute
0.41x
RTX 5880 Ada Generation is 2.46x faster
VRAM
0.25x
RTX 5880 Ada Generation has 4.00x more
Memory Bandwidth
0.70x
RTX 5880 Ada Generation has 1.43x more
NVIDIA T4G
Compute (FP32-eq)
1.69x
Need 1.69x T4G
FP32 Compute
4.20x
Need 4.20x T4G
VRAM
0.75x
T4G has 1.33x more
Memory Bandwidth
2.10x
Need 2.10x T4G
NVIDIA GeForce GTX 1070
Compute (FP32-eq)
8.51x
Need 8.51x GeForce GTX 1070
FP32 Compute
5.26x
Need 5.26x GeForce GTX 1070
VRAM
1.50x
Need 1.50x GeForce GTX 1070
Memory Bandwidth
2.63x
Need 2.63x GeForce GTX 1070
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
1.55x
Need 1.55x GeForce RTX 3090
FP32 Compute
0.96x
GeForce RTX 3090 is 1.05x faster
VRAM
0.50x
GeForce RTX 3090 has 2.00x more
Memory Bandwidth
0.72x
GeForce RTX 3090 has 1.39x more

To match 1x NVIDIA RTX 5880 Ada Generation

Cerebras WSE-3
VRAM
1.09x
Need 1.09x WSE-3
Tenstorrent Wormhole
Compute (FP32-eq)
0.46x
Wormhole is 2.18x faster
VRAM
2.00x
Need 2.00x Wormhole
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
0.46x
RTX 6000 Blackwell is 2.17x faster
FP32 Compute
0.46x
RTX 6000 Blackwell is 2.17x faster
VRAM
0.50x
RTX 6000 Blackwell has 2.00x more
Memory Bandwidth
0.63x
RTX 6000 Blackwell has 1.60x more
NVIDIA GeForce RTX 5070
Compute (FP32-eq)
1.52x
Need 1.52x GeForce RTX 5070
FP32 Compute
2.46x
Need 2.46x GeForce RTX 5070
VRAM
4.00x
Need 4.00x GeForce RTX 5070
Memory Bandwidth
1.43x
Need 1.43x GeForce RTX 5070
NVIDIA T4G
Compute (FP32-eq)
2.57x
Need 2.57x T4G
FP32 Compute
10.31x
Need 10.31x T4G
VRAM
3.00x
Need 3.00x T4G
Memory Bandwidth
3.00x
Need 3.00x T4G
NVIDIA GeForce GTX 1070
Compute (FP32-eq)
12.92x
Need 12.92x GeForce GTX 1070
FP32 Compute
12.92x
Need 12.92x GeForce GTX 1070
VRAM
6.00x
Need 6.00x GeForce GTX 1070
Memory Bandwidth
3.75x
Need 3.75x GeForce GTX 1070
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
2.35x
Need 2.35x GeForce RTX 3090
FP32 Compute
2.35x
Need 2.35x GeForce RTX 3090
VRAM
2.00x
Need 2.00x GeForce RTX 3090
Memory Bandwidth
1.03x
Need 1.03x GeForce RTX 3090

To match 1x NVIDIA T4G

Cerebras WSE-3
VRAM
0.36x
WSE-3 has 2.75x more
Tenstorrent Wormhole
Compute (FP32-eq)
0.18x
Wormhole is 5.60x faster
VRAM
0.67x
Wormhole has 1.50x more
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
0.18x
RTX 6000 Blackwell is 5.57x faster
FP32 Compute
0.04x
RTX 6000 Blackwell is 22.35x faster
VRAM
0.17x
RTX 6000 Blackwell has 6.00x more
Memory Bandwidth
0.21x
RTX 6000 Blackwell has 4.80x more
NVIDIA GeForce RTX 5070
Compute (FP32-eq)
0.59x
GeForce RTX 5070 is 1.69x faster
FP32 Compute
0.24x
GeForce RTX 5070 is 4.20x faster
VRAM
1.33x
Need 1.33x GeForce RTX 5070
Memory Bandwidth
0.48x
GeForce RTX 5070 has 2.10x more
NVIDIA RTX 5880 Ada Generation
Compute (FP32-eq)
0.39x
RTX 5880 Ada Generation is 2.57x faster
FP32 Compute
0.10x
RTX 5880 Ada Generation is 10.31x faster
VRAM
0.33x
RTX 5880 Ada Generation has 3.00x more
Memory Bandwidth
0.33x
RTX 5880 Ada Generation has 3.00x more
NVIDIA GeForce GTX 1070
Compute (FP32-eq)
5.03x
Need 5.03x GeForce GTX 1070
FP32 Compute
1.25x
Need 1.25x GeForce GTX 1070
VRAM
2.00x
Need 2.00x GeForce GTX 1070
Memory Bandwidth
1.25x
Need 1.25x GeForce GTX 1070
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 GTX 1070

Cerebras WSE-3
VRAM
0.18x
WSE-3 has 5.50x more
Tenstorrent Wormhole
Compute (FP32-eq)
0.04x
Wormhole is 28.16x faster
VRAM
0.33x
Wormhole has 3.00x more
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
0.04x
RTX 6000 Blackwell is 28.01x faster
FP32 Compute
0.04x
RTX 6000 Blackwell is 28.01x faster
VRAM
0.08x
RTX 6000 Blackwell has 12.00x more
Memory Bandwidth
0.17x
RTX 6000 Blackwell has 6.00x more
NVIDIA GeForce RTX 5070
Compute (FP32-eq)
0.12x
GeForce RTX 5070 is 8.51x faster
FP32 Compute
0.19x
GeForce RTX 5070 is 5.26x faster
VRAM
0.67x
GeForce RTX 5070 has 1.50x more
Memory Bandwidth
0.38x
GeForce RTX 5070 has 2.63x more
NVIDIA RTX 5880 Ada Generation
Compute (FP32-eq)
0.08x
RTX 5880 Ada Generation is 12.92x faster
FP32 Compute
0.08x
RTX 5880 Ada Generation is 12.92x faster
VRAM
0.17x
RTX 5880 Ada Generation has 6.00x more
Memory Bandwidth
0.27x
RTX 5880 Ada Generation has 3.75x more
NVIDIA T4G
Compute (FP32-eq)
0.20x
T4G is 5.03x faster
FP32 Compute
0.80x
T4G is 1.25x faster
VRAM
0.50x
T4G has 2.00x more
Memory Bandwidth
0.80x
T4G has 1.25x more
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
0.18x
GeForce RTX 3090 is 5.49x faster
FP32 Compute
0.18x
GeForce RTX 3090 is 5.51x faster
VRAM
0.33x
GeForce RTX 3090 has 3.00x more
Memory Bandwidth
0.27x
GeForce RTX 3090 has 3.66x more

To match 1x NVIDIA GeForce RTX 3090

Cerebras WSE-3
VRAM
0.55x
WSE-3 has 1.83x more
Tenstorrent Wormhole
Compute (FP32-eq)
0.20x
Wormhole is 5.13x faster
VRAM
1.00x
Wormhole has 1.00x more
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
0.20x
RTX 6000 Blackwell is 5.10x faster
FP32 Compute
0.20x
RTX 6000 Blackwell is 5.08x faster
VRAM
0.25x
RTX 6000 Blackwell has 4.00x more
Memory Bandwidth
0.61x
RTX 6000 Blackwell has 1.64x more
NVIDIA GeForce RTX 5070
Compute (FP32-eq)
0.65x
GeForce RTX 5070 is 1.55x faster
FP32 Compute
1.05x
Need 1.05x GeForce RTX 5070
VRAM
2.00x
Need 2.00x GeForce RTX 5070
Memory Bandwidth
1.39x
Need 1.39x GeForce RTX 5070
NVIDIA RTX 5880 Ada Generation
Compute (FP32-eq)
0.43x
RTX 5880 Ada Generation is 2.35x faster
FP32 Compute
0.43x
RTX 5880 Ada Generation is 2.35x faster
VRAM
0.50x
RTX 5880 Ada Generation has 2.00x more
Memory Bandwidth
0.97x
RTX 5880 Ada Generation has 1.03x more
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
NVIDIA GeForce GTX 1070
Compute (FP32-eq)
5.49x
Need 5.49x GeForce GTX 1070
FP32 Compute
5.51x
Need 5.51x GeForce GTX 1070
VRAM
3.00x
Need 3.00x GeForce GTX 1070
Memory Bandwidth
3.66x
Need 3.66x GeForce GTX 1070

Pricing

Price TypeWSE-3WormholeRTX 6000 BlackwellGeForce RTX 5070RTX 5880 Ada GenerationT4GGeForce GTX 1070GeForce RTX 3090
CAPEX (Street Price)————————
OPEX (per hour)——$1.26/hr$0.09/hr—$0.42/hr$0.04/hr$0.11/hr
Price per TFLOPs (FP32-eq)————————