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

SpecificationCerebras WSE-3AMD MI325XNVIDIA GeForce RTX 5090NVIDIA RTX 6000 BlackwellNVIDIA GeForce RTX 5060 TiNVIDIA GeForce RTX 3060 TiNVIDIA A100 SXM
ArchitectureWafer Scale EngineCDNA 3.5BlackwellBlackwellBlackwellAmpereAmpere
Form Factor—OAMPCIePCIePCIePCIeSXM
VRAM44 GB256 GB32 GB96 GB16 GB8 GB80 GB
Memory Bandwidth—6,000 GB/s1,792 GB/s1,536 GB/s544 GB/s448 GB/s2,039 GB/s
TFLOPs (FP32)—207921812516.219.5
TFLOPs (FP16)—1,400————312
TFLOPs—1,4003183628833.2312
TFLOPs (FP8)—2,800—————
TDP23000 W800 W575 W300 W220 W200 W400 W
Launch DateMar 2024Oct 2024Jan 2025Jan 2025Mar 2025Dec 2020May 2020

Efficiency Metrics

MetricWSE-3MI325XGeForce RTX 5090RTX 6000 BlackwellGeForce RTX 5060 TiGeForce RTX 3060 TiA100 SXM
TFLOPs per Watt (FP32-eq)—0.880.280.600.200.080.39
Memory Bandwidth per GB—23.4 GB/s56.0 GB/s16.0 GB/s34.0 GB/s56.0 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 Cerebras WSE-3

AMD MI325X
VRAM
0.17x
MI325X has 5.82x more
NVIDIA GeForce RTX 5090
VRAM
1.38x
Need 1.38x GeForce RTX 5090
NVIDIA RTX 6000 Blackwell
VRAM
0.46x
RTX 6000 Blackwell has 2.18x more
NVIDIA GeForce RTX 5060 Ti
VRAM
2.75x
Need 2.75x GeForce RTX 5060 Ti
NVIDIA GeForce RTX 3060 Ti
VRAM
5.50x
Need 5.50x GeForce RTX 3060 Ti
NVIDIA A100 SXM
VRAM
0.55x
A100 SXM has 1.82x more

To match 1x AMD MI325X

Cerebras WSE-3
VRAM
5.82x
Need 5.82x WSE-3
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
4.40x
Need 4.40x GeForce RTX 5090
FP32 Compute
2.25x
Need 2.25x GeForce RTX 5090
VRAM
8.00x
Need 8.00x GeForce RTX 5090
Memory Bandwidth
3.35x
Need 3.35x GeForce RTX 5090
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
3.87x
Need 3.87x RTX 6000 Blackwell
FP32 Compute
1.14x
Need 1.14x RTX 6000 Blackwell
VRAM
2.67x
Need 2.67x RTX 6000 Blackwell
Memory Bandwidth
3.91x
Need 3.91x RTX 6000 Blackwell
NVIDIA GeForce RTX 5060 Ti
Compute (FP32-eq)
15.91x
Need 15.91x GeForce RTX 5060 Ti
FP32 Compute
8.28x
Need 8.28x GeForce RTX 5060 Ti
VRAM
16.00x
Need 16.00x GeForce RTX 5060 Ti
Memory Bandwidth
11.03x
Need 11.03x GeForce RTX 5060 Ti
NVIDIA GeForce RTX 3060 Ti
Compute (FP32-eq)
42.17x
Need 42.17x GeForce RTX 3060 Ti
FP32 Compute
12.78x
Need 12.78x GeForce RTX 3060 Ti
VRAM
32.00x
Need 32.00x GeForce RTX 3060 Ti
Memory Bandwidth
13.39x
Need 13.39x GeForce RTX 3060 Ti
NVIDIA A100 SXM
Compute (FP32-eq)
4.49x
Need 4.49x A100 SXM
FP32 Compute
10.62x
Need 10.62x A100 SXM
VRAM
3.20x
Need 3.20x A100 SXM
Memory Bandwidth
2.94x
Need 2.94x A100 SXM

To match 1x NVIDIA GeForce RTX 5090

Cerebras WSE-3
VRAM
0.73x
WSE-3 has 1.38x more
AMD MI325X
Compute (FP32-eq)
0.23x
MI325X is 4.40x faster
FP32 Compute
0.44x
MI325X is 2.25x faster
VRAM
0.13x
MI325X has 8.00x more
Memory Bandwidth
0.30x
MI325X has 3.35x more
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
0.88x
RTX 6000 Blackwell is 1.14x faster
FP32 Compute
0.51x
RTX 6000 Blackwell is 1.97x faster
VRAM
0.33x
RTX 6000 Blackwell has 3.00x more
Memory Bandwidth
1.17x
Need 1.17x RTX 6000 Blackwell
NVIDIA GeForce RTX 5060 Ti
Compute (FP32-eq)
3.61x
Need 3.61x GeForce RTX 5060 Ti
FP32 Compute
3.68x
Need 3.68x GeForce RTX 5060 Ti
VRAM
2.00x
Need 2.00x GeForce RTX 5060 Ti
Memory Bandwidth
3.29x
Need 3.29x GeForce RTX 5060 Ti
NVIDIA GeForce RTX 3060 Ti
Compute (FP32-eq)
9.58x
Need 9.58x GeForce RTX 3060 Ti
FP32 Compute
5.68x
Need 5.68x GeForce RTX 3060 Ti
VRAM
4.00x
Need 4.00x GeForce RTX 3060 Ti
Memory Bandwidth
4.00x
Need 4.00x GeForce RTX 3060 Ti
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 RTX 6000 Blackwell

Cerebras WSE-3
VRAM
2.18x
Need 2.18x WSE-3
AMD MI325X
Compute (FP32-eq)
0.26x
MI325X is 3.87x faster
FP32 Compute
0.87x
MI325X is 1.14x faster
VRAM
0.38x
MI325X has 2.67x more
Memory Bandwidth
0.26x
MI325X has 3.91x more
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
1.14x
Need 1.14x GeForce RTX 5090
FP32 Compute
1.97x
Need 1.97x GeForce RTX 5090
VRAM
3.00x
Need 3.00x GeForce RTX 5090
Memory Bandwidth
0.86x
GeForce RTX 5090 has 1.17x more
NVIDIA GeForce RTX 5060 Ti
Compute (FP32-eq)
4.11x
Need 4.11x GeForce RTX 5060 Ti
FP32 Compute
7.24x
Need 7.24x GeForce RTX 5060 Ti
VRAM
6.00x
Need 6.00x GeForce RTX 5060 Ti
Memory Bandwidth
2.82x
Need 2.82x GeForce RTX 5060 Ti
NVIDIA GeForce RTX 3060 Ti
Compute (FP32-eq)
10.90x
Need 10.90x GeForce RTX 3060 Ti
FP32 Compute
11.17x
Need 11.17x GeForce RTX 3060 Ti
VRAM
12.00x
Need 12.00x GeForce RTX 3060 Ti
Memory Bandwidth
3.43x
Need 3.43x GeForce RTX 3060 Ti
NVIDIA A100 SXM
Compute (FP32-eq)
1.16x
Need 1.16x A100 SXM
FP32 Compute
9.28x
Need 9.28x A100 SXM
VRAM
1.20x
Need 1.20x A100 SXM
Memory Bandwidth
0.75x
A100 SXM has 1.33x more

To match 1x NVIDIA GeForce RTX 5060 Ti

Cerebras WSE-3
VRAM
0.36x
WSE-3 has 2.75x more
AMD MI325X
Compute (FP32-eq)
0.06x
MI325X is 15.91x faster
FP32 Compute
0.12x
MI325X is 8.28x faster
VRAM
0.06x
MI325X has 16.00x more
Memory Bandwidth
0.09x
MI325X has 11.03x more
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
0.28x
GeForce RTX 5090 is 3.61x faster
FP32 Compute
0.27x
GeForce RTX 5090 is 3.68x faster
VRAM
0.50x
GeForce RTX 5090 has 2.00x more
Memory Bandwidth
0.30x
GeForce RTX 5090 has 3.29x more
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
0.24x
RTX 6000 Blackwell is 4.11x faster
FP32 Compute
0.14x
RTX 6000 Blackwell is 7.24x faster
VRAM
0.17x
RTX 6000 Blackwell has 6.00x more
Memory Bandwidth
0.35x
RTX 6000 Blackwell has 2.82x more
NVIDIA GeForce RTX 3060 Ti
Compute (FP32-eq)
2.65x
Need 2.65x GeForce RTX 3060 Ti
FP32 Compute
1.54x
Need 1.54x GeForce RTX 3060 Ti
VRAM
2.00x
Need 2.00x GeForce RTX 3060 Ti
Memory Bandwidth
1.21x
Need 1.21x GeForce RTX 3060 Ti
NVIDIA A100 SXM
Compute (FP32-eq)
0.28x
A100 SXM is 3.55x faster
FP32 Compute
1.28x
Need 1.28x A100 SXM
VRAM
0.20x
A100 SXM has 5.00x more
Memory Bandwidth
0.27x
A100 SXM has 3.75x more

To match 1x NVIDIA GeForce RTX 3060 Ti

Cerebras WSE-3
VRAM
0.18x
WSE-3 has 5.50x more
AMD MI325X
Compute (FP32-eq)
0.02x
MI325X is 42.17x faster
FP32 Compute
0.08x
MI325X is 12.78x faster
VRAM
0.03x
MI325X has 32.00x more
Memory Bandwidth
0.07x
MI325X has 13.39x more
NVIDIA GeForce RTX 5090
Compute (FP32-eq)
0.10x
GeForce RTX 5090 is 9.58x faster
FP32 Compute
0.18x
GeForce RTX 5090 is 5.68x faster
VRAM
0.25x
GeForce RTX 5090 has 4.00x more
Memory Bandwidth
0.25x
GeForce RTX 5090 has 4.00x more
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
0.09x
RTX 6000 Blackwell is 10.90x faster
FP32 Compute
0.09x
RTX 6000 Blackwell is 11.17x faster
VRAM
0.08x
RTX 6000 Blackwell has 12.00x more
Memory Bandwidth
0.29x
RTX 6000 Blackwell has 3.43x more
NVIDIA GeForce RTX 5060 Ti
Compute (FP32-eq)
0.38x
GeForce RTX 5060 Ti is 2.65x faster
FP32 Compute
0.65x
GeForce RTX 5060 Ti is 1.54x faster
VRAM
0.50x
GeForce RTX 5060 Ti has 2.00x more
Memory Bandwidth
0.82x
GeForce RTX 5060 Ti has 1.21x more
NVIDIA A100 SXM
Compute (FP32-eq)
0.11x
A100 SXM is 9.40x faster
FP32 Compute
0.83x
A100 SXM is 1.20x faster
VRAM
0.10x
A100 SXM has 10.00x more
Memory Bandwidth
0.22x
A100 SXM has 4.55x more

To match 1x NVIDIA A100 SXM

Cerebras WSE-3
VRAM
1.82x
Need 1.82x WSE-3
AMD MI325X
Compute (FP32-eq)
0.22x
MI325X is 4.49x faster
FP32 Compute
0.09x
MI325X is 10.62x faster
VRAM
0.31x
MI325X has 3.20x more
Memory Bandwidth
0.34x
MI325X has 2.94x 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 RTX 6000 Blackwell
Compute (FP32-eq)
0.86x
RTX 6000 Blackwell is 1.16x faster
FP32 Compute
0.11x
RTX 6000 Blackwell is 9.28x faster
VRAM
0.83x
RTX 6000 Blackwell has 1.20x more
Memory Bandwidth
1.33x
Need 1.33x RTX 6000 Blackwell
NVIDIA GeForce RTX 5060 Ti
Compute (FP32-eq)
3.55x
Need 3.55x GeForce RTX 5060 Ti
FP32 Compute
0.78x
GeForce RTX 5060 Ti is 1.28x faster
VRAM
5.00x
Need 5.00x GeForce RTX 5060 Ti
Memory Bandwidth
3.75x
Need 3.75x GeForce RTX 5060 Ti
NVIDIA GeForce RTX 3060 Ti
Compute (FP32-eq)
9.40x
Need 9.40x GeForce RTX 3060 Ti
FP32 Compute
1.20x
Need 1.20x GeForce RTX 3060 Ti
VRAM
10.00x
Need 10.00x GeForce RTX 3060 Ti
Memory Bandwidth
4.55x
Need 4.55x GeForce RTX 3060 Ti

Pricing

Price TypeWSE-3MI325XGeForce RTX 5090RTX 6000 BlackwellGeForce RTX 5060 TiGeForce RTX 3060 TiA100 SXM
CAPEX (Street Price)—$45,000————$15,000
OPEX (per hour)—$36.92/hr$0.27/hr$1.26/hr$0.09/hr$0.05/hr$4.05/hr
Price per TFLOPs (FP32-eq)—$64————$96