NVIDIA GeForce GTX 1660 vs NVIDIA GeForce RTX 3090 Ti — Spécifications, performances, tests

Differences Spécifications Benchmarks Témoignages

Differences

Raisons de considérer
NVIDIA GeForce GTX 1660

Signaler un bogue

Raisons de considérer
NVIDIA GeForce RTX 3090 Ti

Signaler un bogue

Vitesse d'horloge plus élevée

Autour de 2% une meilleure vitesse d'horloge

1.56 GHz 1.53 GHz
Plus de mémoire

300% de mémoire supplémentaire

24 GB 6 GB

Positions dans tous les classements

Positions communes NVIDIA GeForce RTX 3090 Ti GPU dans des benchmarks populaires, pour comparaison avec d'autres modèles.

Passmark Performance Test GPU

1 place

Spécifications

Données techniques

NVIDIA GeForce GTX 1660

NVIDIA GeForce RTX 3090 Ti

Informations générales

Comparaison des données techniques de base des cartes graphiques NVIDIA GeForce GTX 1660 et NVIDIA GeForce RTX 3090 Ti, puce, unités de traitement de l'information.

Architecture

Turing Ampere
CUDA Cores

1408 10752
Execution Units

1408 -
Puce GPU

TU116 GA102-350-A1
L1 Cache

64 KB 128 KB
L2 Cache

1.536 MB 6 MB
Unités de sortie de rendu

48 112
Unités de texture

88 336
Sur la base de

- GA102
Shader

- 10752

Paramètres de la mémoire

Video memory capacity, type, bus width and bandwidth describe different properties. These values alone do not determine graphics performance.

Memory Bandwidth

192.1 GB/s 1,008 GB/s
Memory Bus

192 bit 384 bit
Memory Clock

2000 MHz -
Memory Data Rate

8 Gbps -
Taille de la mémoire

6 GB 24 GB
Type de mémoire

GDDR5 GDDR6X
Memory Speed (legacy frequency label)

- 1300 MHz

Fréquence d'horloge

Published GPU clock frequencies describe different operating modes. Clock speed alone does not determine graphics performance.

Fréquence de base

1530 MHz 1560 MHz
Fréquence maximale

1785 MHz 1860 MHz
Overclocking

- Non

Consommation d'énergie

Graphics card power limits and recommended system power supply describe different specifications.

Graphics Card Power

120 W 450 W
Maximum GPU Temperature

95 °C 92 °C
System Power Supply

450 W (Minimum system power requirement) 850 W (System power requirement)
TDP

120 W 450 W

Interfaces

Connectivité et connexions.

DisplayPort Ports

1 × DisplayPort 1.4a 3 × DisplayPort 1.4a
Ports DVI

1 × DVI -
Ports HDMI

1 × HDMI 2.0 1 × HDMI 2.1
Max. Affichages

3 4
Other Display Outputs (unparsed)

DP 1.4a; HDMI 2.0b; DL-DVI-D HDMI
PCIe Interface

PCIe 3.0 x16 PCIe 4.0 x16
Power Connectors

8-pin 3x PCIe 8-pin cables (adapter in box) OR 450W or greater PCIe Gen 5 cable
HDCP Version

- 2.3

Données techniques

Des données techniques utilisées à leur plein potentiel dans les jeux informatiques.

CUDA

7.5 -
DirectX

12.1 12_2
Résolution maximale

3840 × 2160 7680 × 4320
OpenCL

3.0 3.0
OpenGL

4.6 4.6
Shader Model

6.7 (6.4) 6.6
Vulkan

1.3 1.3

Dimensions

La différence de taille, de poids et de fente des appareils comparés

Hauteur

35 mm -
Longueur

229 mm -
Slot Size

Dual-slot -
Width

111 mm -

Plus d'informations

Comparaison des interfaces et des dates de sortie des GPU NVIDIA GeForce RTX 3090 Ti et NVIDIA GeForce GTX 1660.

Manufacturer specification scope

NVIDIA Founders Edition/reference design. Clock specifications apply to gaming use. AIB shipping specifications and complete-system power needs may differ. NVIDIA Founders Edition/reference design. Clock specifications apply to gaming use. AIB shipping specifications and complete-system power needs may differ.
Multi-monitor support

Oui -
Process Technology

12 nm 8 nm
Date de sortie

Q1/2019 -

Theoretical Performance

FP16 (theoretical)

10.05 TFLOPS (2:1) 40 TFLOPS
FP32 (theoretical)

5.027 TFLOPS 40 TFLOPS
FP64 (theoretical)

157.1 GFLOPS (1:32) 0.625 TFLOPS
Pixel Rate

85.68 GPixel/s 208.3 GPixel/s
Texture Rate

157.1 GTexel/s 625.0 GTexel/s

Benchmarks

Tests de performance GPUs

Shared tests with results for both models: 9

Blender Cycles

Each row uses one Blender version, operating system and compute backend.

Test and settings	NVIDIA GeForce GTX 1660	NVIDIA GeForce RTX 3090 Ti	Result difference¹
Blender 5.1.1 / OPTIX / Windows	595.520496 samples/min Submissions: 6	5459.157697 samples/min Submissions: 5	+816.7 %
Blender 4.5.0 / OPTIX / Windows	675.939963 samples/min Submissions: 20	5585.151795 samples/min Submissions: 115	+726.3 %
Blender 4.4.0 / OPTIX / Windows	675.243544 samples/min Submissions: 13	5700.575741 samples/min Submissions: 51	+744.2 %
Blender 4.3.0 / OPTIX / Linux	690.741064 samples/min Submissions: 5	5840.23445 samples/min Submissions: 8	+745.5 %
Blender 4.3.0 / OPTIX / Windows	677.894173 samples/min Submissions: 13	5490.159484 samples/min Submissions: 35	+709.9 %
Blender 4.2.0 / OPTIX / Windows	689.203496 samples/min Submissions: 15	5673.136912 samples/min Submissions: 51	+723.1 %
Blender 4.1.0 / OPTIX / Windows	695.468717 samples/min Submissions: 24	5769.869986 samples/min Submissions: 32	+729.6 %
Blender 4.0.0 / OPTIX / Linux	701.451067 samples/min Submissions: 5	6168.026652 samples/min Submissions: 16	+779.3 %
Blender 4.0.0 / OPTIX / Windows	696.090828 samples/min Submissions: 26	5124.064923 samples/min Submissions: 111	+636.1 %

¹ Difference of the second result relative to the first in that row. No percentage is calculated for different upscaling algorithms. This compares published results, not a universal performance index.

Individual model tests

These results have no shared test of both models with the same version and settings. They are shown separately without a percentage difference.