Compare XPUs

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

Select XPUs to Compare

Clear all (9)Jump to results
Showing 128 XPUs • 9 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

SpecificationSambaNova SN40LGoogle TPU v5pAMD MI300XNVIDIA RTX 6000 BlackwellNVIDIA GeForce RTX 3090NVIDIA GH200NVIDIA A100 SXMNVIDIA T4NVIDIA GeForce GTX 1080
ArchitectureReconfigurable Dataflow Unit (RDU)TPU v5CDNA 3BlackwellAmpereHopperAmpereTuringPascal
Form Factor—MezzanineOAMPCIePCIeSXMSXMPCIePCIe
VRAM640 GB95 GB192 GB96 GB24 GB96 GB80 GB16 GB8 GB
Memory Bandwidth——5,300 GB/s1,536 GB/s936 GB/s4,000 GB/s2,039 GB/s320 GB/s320 GB/s
TFLOPs (FP32)——163.418135.66719.58.18.873
TFLOPs (FP16)——1,307———312——
TFLOPs—4591,30736271989312658.873
TFLOPs (FP8)——2,614——————
TDP700 W400 W750 W300 W350 W1000 W400 W70 W180 W
Launch DateJan 2024Aug 2023Dec 2023Jan 2025Sep 2020May 2023May 2020Sep 2018May 2016

Efficiency Metrics

MetricSN40LTPU v5pMI300XRTX 6000 BlackwellGeForce RTX 3090GH200A100 SXMT4GeForce GTX 1080
TFLOPs per Watt (FP32-eq)—0.570.870.600.100.490.390.460.05
Memory Bandwidth per GB——27.6 GB/s16.0 GB/s39.0 GB/s41.7 GB/s25.5 GB/s20.0 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 SambaNova SN40L

Google TPU v5p
VRAM
6.74x
Need 6.74x TPU v5p
AMD MI300X
VRAM
3.33x
Need 3.33x MI300X
NVIDIA RTX 6000 Blackwell
VRAM
6.67x
Need 6.67x RTX 6000 Blackwell
NVIDIA GeForce RTX 3090
VRAM
26.67x
Need 26.67x GeForce RTX 3090
NVIDIA GH200
VRAM
6.67x
Need 6.67x GH200
NVIDIA A100 SXM
VRAM
8.00x
Need 8.00x A100 SXM
NVIDIA T4
VRAM
40.00x
Need 40.00x T4
NVIDIA GeForce GTX 1080
VRAM
80.00x
Need 80.00x GeForce GTX 1080

To match 1x Google TPU v5p

SambaNova SN40L
VRAM
0.15x
SN40L has 6.74x more
AMD MI300X
Compute (FP32-eq)
0.35x
MI300X is 2.85x faster
VRAM
0.49x
MI300X has 2.02x more
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
1.27x
Need 1.27x RTX 6000 Blackwell
VRAM
0.99x
RTX 6000 Blackwell has 1.01x more
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
6.46x
Need 6.46x GeForce RTX 3090
VRAM
3.96x
Need 3.96x GeForce RTX 3090
NVIDIA GH200
Compute (FP32-eq)
0.46x
GH200 is 2.15x faster
VRAM
0.99x
GH200 has 1.01x more
NVIDIA A100 SXM
Compute (FP32-eq)
1.47x
Need 1.47x A100 SXM
VRAM
1.19x
Need 1.19x A100 SXM
NVIDIA T4
Compute (FP32-eq)
7.06x
Need 7.06x T4
VRAM
5.94x
Need 5.94x T4
NVIDIA GeForce GTX 1080
Compute (FP32-eq)
25.86x
Need 25.86x GeForce GTX 1080
VRAM
11.88x
Need 11.88x GeForce GTX 1080

To match 1x AMD MI300X

SambaNova SN40L
VRAM
0.30x
SN40L has 3.33x more
Google TPU v5p
Compute (FP32-eq)
2.85x
Need 2.85x TPU v5p
VRAM
2.02x
Need 2.02x TPU v5p
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
3.61x
Need 3.61x RTX 6000 Blackwell
FP32 Compute
0.90x
RTX 6000 Blackwell is 1.11x faster
VRAM
2.00x
Need 2.00x RTX 6000 Blackwell
Memory Bandwidth
3.45x
Need 3.45x RTX 6000 Blackwell
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 GH200
Compute (FP32-eq)
1.32x
Need 1.32x GH200
FP32 Compute
2.44x
Need 2.44x GH200
VRAM
2.00x
Need 2.00x GH200
Memory Bandwidth
1.32x
Need 1.32x GH200
NVIDIA A100 SXM
Compute (FP32-eq)
4.19x
Need 4.19x A100 SXM
FP32 Compute
8.38x
Need 8.38x A100 SXM
VRAM
2.40x
Need 2.40x A100 SXM
Memory Bandwidth
2.60x
Need 2.60x A100 SXM
NVIDIA T4
Compute (FP32-eq)
20.11x
Need 20.11x T4
FP32 Compute
20.17x
Need 20.17x T4
VRAM
12.00x
Need 12.00x T4
Memory Bandwidth
16.56x
Need 16.56x T4
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 NVIDIA RTX 6000 Blackwell

SambaNova SN40L
VRAM
0.15x
SN40L has 6.67x more
Google TPU v5p
Compute (FP32-eq)
0.79x
TPU v5p is 1.27x faster
VRAM
1.01x
Need 1.01x TPU v5p
AMD MI300X
Compute (FP32-eq)
0.28x
MI300X is 3.61x faster
FP32 Compute
1.11x
Need 1.11x MI300X
VRAM
0.50x
MI300X has 2.00x more
Memory Bandwidth
0.29x
MI300X has 3.45x more
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
NVIDIA GH200
Compute (FP32-eq)
0.37x
GH200 is 2.73x faster
FP32 Compute
2.70x
Need 2.70x GH200
VRAM
1.00x
GH200 has 1.00x more
Memory Bandwidth
0.38x
GH200 has 2.60x more
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
NVIDIA T4
Compute (FP32-eq)
5.57x
Need 5.57x T4
FP32 Compute
22.35x
Need 22.35x T4
VRAM
6.00x
Need 6.00x T4
Memory Bandwidth
4.80x
Need 4.80x T4
NVIDIA GeForce GTX 1080
Compute (FP32-eq)
20.40x
Need 20.40x GeForce GTX 1080
FP32 Compute
20.40x
Need 20.40x GeForce GTX 1080
VRAM
12.00x
Need 12.00x GeForce GTX 1080
Memory Bandwidth
4.80x
Need 4.80x GeForce GTX 1080

To match 1x NVIDIA GeForce RTX 3090

SambaNova SN40L
VRAM
0.04x
SN40L has 26.67x more
Google TPU v5p
Compute (FP32-eq)
0.15x
TPU v5p is 6.46x faster
VRAM
0.25x
TPU v5p has 3.96x more
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
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 GH200
Compute (FP32-eq)
0.07x
GH200 is 13.93x faster
FP32 Compute
0.53x
GH200 is 1.88x faster
VRAM
0.25x
GH200 has 4.00x more
Memory Bandwidth
0.23x
GH200 has 4.27x more
NVIDIA A100 SXM
Compute (FP32-eq)
0.23x
A100 SXM is 4.39x faster
FP32 Compute
1.83x
Need 1.83x A100 SXM
VRAM
0.30x
A100 SXM has 3.33x more
Memory Bandwidth
0.46x
A100 SXM has 2.18x more
NVIDIA T4
Compute (FP32-eq)
1.09x
Need 1.09x T4
FP32 Compute
4.40x
Need 4.40x T4
VRAM
1.50x
Need 1.50x T4
Memory Bandwidth
2.92x
Need 2.92x T4
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 GH200

SambaNova SN40L
VRAM
0.15x
SN40L has 6.67x more
Google TPU v5p
Compute (FP32-eq)
2.15x
Need 2.15x TPU v5p
VRAM
1.01x
Need 1.01x TPU v5p
AMD MI300X
Compute (FP32-eq)
0.76x
MI300X is 1.32x faster
FP32 Compute
0.41x
MI300X is 2.44x faster
VRAM
0.50x
MI300X has 2.00x more
Memory Bandwidth
0.75x
MI300X has 1.32x more
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
2.73x
Need 2.73x RTX 6000 Blackwell
FP32 Compute
0.37x
RTX 6000 Blackwell is 2.70x faster
VRAM
1.00x
RTX 6000 Blackwell has 1.00x more
Memory Bandwidth
2.60x
Need 2.60x RTX 6000 Blackwell
NVIDIA GeForce RTX 3090
Compute (FP32-eq)
13.93x
Need 13.93x GeForce RTX 3090
FP32 Compute
1.88x
Need 1.88x GeForce RTX 3090
VRAM
4.00x
Need 4.00x GeForce RTX 3090
Memory Bandwidth
4.27x
Need 4.27x GeForce RTX 3090
NVIDIA A100 SXM
Compute (FP32-eq)
3.17x
Need 3.17x A100 SXM
FP32 Compute
3.44x
Need 3.44x A100 SXM
VRAM
1.20x
Need 1.20x A100 SXM
Memory Bandwidth
1.96x
Need 1.96x A100 SXM
NVIDIA T4
Compute (FP32-eq)
15.22x
Need 15.22x T4
FP32 Compute
8.27x
Need 8.27x T4
VRAM
6.00x
Need 6.00x T4
Memory Bandwidth
12.50x
Need 12.50x T4
NVIDIA GeForce GTX 1080
Compute (FP32-eq)
55.73x
Need 55.73x GeForce GTX 1080
FP32 Compute
7.55x
Need 7.55x GeForce GTX 1080
VRAM
12.00x
Need 12.00x GeForce GTX 1080
Memory Bandwidth
12.50x
Need 12.50x GeForce GTX 1080

To match 1x NVIDIA A100 SXM

SambaNova SN40L
VRAM
0.13x
SN40L has 8.00x more
Google TPU v5p
Compute (FP32-eq)
0.68x
TPU v5p is 1.47x faster
VRAM
0.84x
TPU v5p has 1.19x more
AMD MI300X
Compute (FP32-eq)
0.24x
MI300X is 4.19x faster
FP32 Compute
0.12x
MI300X is 8.38x faster
VRAM
0.42x
MI300X has 2.40x more
Memory Bandwidth
0.38x
MI300X has 2.60x more
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 3090
Compute (FP32-eq)
4.39x
Need 4.39x GeForce RTX 3090
FP32 Compute
0.55x
GeForce RTX 3090 is 1.83x faster
VRAM
3.33x
Need 3.33x GeForce RTX 3090
Memory Bandwidth
2.18x
Need 2.18x GeForce RTX 3090
NVIDIA GH200
Compute (FP32-eq)
0.32x
GH200 is 3.17x faster
FP32 Compute
0.29x
GH200 is 3.44x faster
VRAM
0.83x
GH200 has 1.20x more
Memory Bandwidth
0.51x
GH200 has 1.96x more
NVIDIA T4
Compute (FP32-eq)
4.80x
Need 4.80x T4
FP32 Compute
2.41x
Need 2.41x T4
VRAM
5.00x
Need 5.00x T4
Memory Bandwidth
6.37x
Need 6.37x T4
NVIDIA GeForce GTX 1080
Compute (FP32-eq)
17.58x
Need 17.58x GeForce GTX 1080
FP32 Compute
2.20x
Need 2.20x GeForce GTX 1080
VRAM
10.00x
Need 10.00x GeForce GTX 1080
Memory Bandwidth
6.37x
Need 6.37x GeForce GTX 1080

To match 1x NVIDIA T4

SambaNova SN40L
VRAM
0.03x
SN40L has 40.00x more
Google TPU v5p
Compute (FP32-eq)
0.14x
TPU v5p is 7.06x faster
VRAM
0.17x
TPU v5p has 5.94x more
AMD MI300X
Compute (FP32-eq)
0.05x
MI300X is 20.11x faster
FP32 Compute
0.05x
MI300X is 20.17x faster
VRAM
0.08x
MI300X has 12.00x more
Memory Bandwidth
0.06x
MI300X has 16.56x 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 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
NVIDIA GH200
Compute (FP32-eq)
0.07x
GH200 is 15.22x faster
FP32 Compute
0.12x
GH200 is 8.27x faster
VRAM
0.17x
GH200 has 6.00x more
Memory Bandwidth
0.08x
GH200 has 12.50x more
NVIDIA A100 SXM
Compute (FP32-eq)
0.21x
A100 SXM is 4.80x faster
FP32 Compute
0.42x
A100 SXM is 2.41x faster
VRAM
0.20x
A100 SXM has 5.00x more
Memory Bandwidth
0.16x
A100 SXM has 6.37x more
NVIDIA GeForce GTX 1080
Compute (FP32-eq)
3.66x
Need 3.66x GeForce GTX 1080
FP32 Compute
0.91x
GeForce GTX 1080 is 1.10x faster
VRAM
2.00x
Need 2.00x GeForce GTX 1080
Memory Bandwidth
1.00x
GeForce GTX 1080 has 1.00x more

To match 1x NVIDIA GeForce GTX 1080

SambaNova SN40L
VRAM
0.01x
SN40L has 80.00x more
Google TPU v5p
Compute (FP32-eq)
0.04x
TPU v5p is 25.86x faster
VRAM
0.08x
TPU v5p has 11.88x more
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
NVIDIA RTX 6000 Blackwell
Compute (FP32-eq)
0.05x
RTX 6000 Blackwell is 20.40x faster
FP32 Compute
0.05x
RTX 6000 Blackwell is 20.40x faster
VRAM
0.08x
RTX 6000 Blackwell has 12.00x more
Memory Bandwidth
0.21x
RTX 6000 Blackwell has 4.80x 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
NVIDIA GH200
Compute (FP32-eq)
0.02x
GH200 is 55.73x faster
FP32 Compute
0.13x
GH200 is 7.55x faster
VRAM
0.08x
GH200 has 12.00x more
Memory Bandwidth
0.08x
GH200 has 12.50x more
NVIDIA A100 SXM
Compute (FP32-eq)
0.06x
A100 SXM is 17.58x faster
FP32 Compute
0.46x
A100 SXM is 2.20x faster
VRAM
0.10x
A100 SXM has 10.00x more
Memory Bandwidth
0.16x
A100 SXM has 6.37x more
NVIDIA T4
Compute (FP32-eq)
0.27x
T4 is 3.66x faster
FP32 Compute
1.10x
Need 1.10x T4
VRAM
0.50x
T4 has 2.00x more
Memory Bandwidth
1.00x
T4 has 1.00x more

Pricing

Price TypeSN40LTPU v5pMI300XRTX 6000 BlackwellGeForce RTX 3090GH200A100 SXMT4GeForce GTX 1080
CAPEX (Street Price)——$35,000———$15,000——
OPEX (per hour)—$5.00/hr$10.40/hr$1.26/hr$0.11/hr$1.49/hr$4.05/hr$0.27/hr$0.04/hr
Price per TFLOPs (FP32-eq)——$54———$96——