EVGA GTX 660 3 GB vs NVIDIA A100 PCIe 80 GB

Comparison of EVGA GTX 660 3 GB with 3 GB GDDR5 and 960 cores vs NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores.

Loading...

Performance Rating

NVIDIA A100 PCIe 80 GB outperforms EVGA GTX 660 3 GB by 1,241.88% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

EVGA GTX 660 3 GB

1.9

EVGA GTX 660 3 GB

1.9
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA A100 PCIe 80 GB

25.6

NVIDIA A100 PCIe 80 GB

25.6

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Additional

Memory

Memory Size

3 ГБ
🔥 +2,567% 80 ГБ

Memory Type

GDDR5 HBM2e

Memory Bandwidth

144.2 GB/s
🔥 1.94 TB/s

Memory Bus Width

192 бит 5,120 бит

ML Performance

FP16 (Half Precision)

No
🔥 77.97 TFLOPS

BF16 (Brain Float)

No
🔥 311.84 TFLOPS

TF32 (TensorFloat)

No
🔥 155.92

Compute Power

FP32 (Single Precision)

1.981 TFLOPS
🔥 +884% 19.49 TFLOPS

FP64 (Double Precision)

0.08256000000000001 TFLOPS
🔥 +11,705% 9.746 TFLOPS

CUDA Cores

960
🔥 +620% 6,912

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Kepler Ampere

SM (Streaming Multiprocessor)

No
🔥 108

PCIe Version

PCIe 3.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

3.0
🔥 8.0

Clocks & Performance

Base Clock

980
🔥 +9% 1,065

Boost Clock

1,032
🔥 +37% 1,410

Memory Clock

1,502
🔥 +1% 1,512

Power Consumption

TDP/TGP

🔥 -53% 140 W
300 W

Recommended PSU

🔥 -57% 300 W
700 W

Power Connector

1x 6-pin 8-pin EPS

Rendering

Texture Units (TMU)

80
🔥 +440% 432

ROP

No No

L2 Cache

384 KB
🔥 80 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

Sept. 6, 2012 June 28, 2021

Display Outputs

2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
No outputs

Renting is cheaper than buying