NVIDIA GeForce RTX 3070 versus NVIDIA GeForce GTX 1660 SUPER

Comparaison des cartes vidéo NVIDIA GeForce RTX 3070 and NVIDIA GeForce GTX 1660 SUPER pour tous les caractéristiques connus dans les catégories suivants: Essentiel, Infos techniques, Sorties et ports de vidéo, Compatibilité, dimensions et exigences, Soutien API, Mémoire. Analyse du performance de référence des cartes vidéo: PassMark - G3D Mark, PassMark - G2D Mark, Geekbench - OpenCL, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps), 3DMark Fire Strike - Graphics Score.

NVIDIA GeForce RTX 3070

versus

NVIDIA GeForce GTX 1660 SUPER

Différences

Raisons pour considerer le NVIDIA GeForce RTX 3070

La carte vidéo est plus nouvelle: date de sortie 10 mois plus tard
times}x plus de taux de remplissage de la texture: 317.4 GTexel/s versus 157.1 GTexel/s
4.2x plus de pipelines: 5888 versus 1408
Un nouveau processus de fabrication soutient une carte vidéo plus forte, mais moins chaude: 8 nm versus 12 nm
Environ 33% plus de taille maximale de mémoire: 8 GB versus 6 GB
Environ 75% meilleur performance en PassMark - G3D Mark: 22253 versus 12712
Environ 24% meilleur performance en PassMark - G2D Mark: 999 versus 804
Environ 97% meilleur performance en Geekbench - OpenCL: 123479 versus 62641
2.4x meilleur performance en CompuBench 1.5 Desktop - Face Detection (mPixels/s): 453.922 versus 187.131
2.3x meilleur performance en CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 5803.174 versus 2548.187
2.6x meilleur performance en CompuBench 1.5 Desktop - T-Rex (Frames/s): 40.757 versus 15.882
Environ 55% meilleur performance en CompuBench 1.5 Desktop - Video Composition (Frames/s): 182.055 versus 117.673
Environ 85% meilleur performance en CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 1664.554 versus 901.388
Environ 78% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Frames): 31716 versus 17812
3.6x meilleur performance en GFXBench 4.0 - Manhattan (Frames): 13566 versus 3717
9.5x meilleur performance en GFXBench 4.0 - T-Rex (Frames): 31930 versus 3351
Environ 78% meilleur performance en GFXBench 4.0 - Car Chase Offscreen (Fps): 31716 versus 17812
3.6x meilleur performance en GFXBench 4.0 - Manhattan (Fps): 13566 versus 3717
9.5x meilleur performance en GFXBench 4.0 - T-Rex (Fps): 31930 versus 3351
2.5x meilleur performance en 3DMark Fire Strike - Graphics Score: 3163 versus 1278

Caractéristiques
Date de sortie	1 Sep 2020 versus 29 Oct 2019
Taux de remplissage de la texture	317.4 GTexel/s versus 157.1 GTexel/s
Pipelines	5888 versus 1408
Processus de fabrication	8 nm versus 12 nm
Taille de mémore maximale	8 GB versus 6 GB
Référence
PassMark - G3D Mark	22253 versus 12712
PassMark - G2D Mark	999 versus 804
Geekbench - OpenCL	123479 versus 62641
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	453.922 versus 187.131
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	5803.174 versus 2548.187
CompuBench 1.5 Desktop - T-Rex (Frames/s)	40.757 versus 15.882
CompuBench 1.5 Desktop - Video Composition (Frames/s)	182.055 versus 117.673
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	1664.554 versus 901.388
GFXBench 4.0 - Car Chase Offscreen (Frames)	31716 versus 17812
GFXBench 4.0 - Manhattan (Frames)	13566 versus 3717
GFXBench 4.0 - T-Rex (Frames)	31930 versus 3351
GFXBench 4.0 - Car Chase Offscreen (Fps)	31716 versus 17812
GFXBench 4.0 - Manhattan (Fps)	13566 versus 3717
GFXBench 4.0 - T-Rex (Fps)	31930 versus 3351
3DMark Fire Strike - Graphics Score	3163 versus 1278

Raisons pour considerer le NVIDIA GeForce GTX 1660 SUPER

Environ 2% plus haut vitesse du noyau: 1530 MHz versus 1500 MHz
Environ 3% plus de la vitesse augmenté: 1785 MHz versus 1725 MHz
Environ 76% consummation d’énergie moyen plus bas: 125 Watt versus 220 Watt

Vitesse du noyau	1530 MHz versus 1500 MHz
Vitesse augmenté	1785 MHz versus 1725 MHz
Thermal Design Power (TDP)	125 Watt versus 220 Watt

Comparer les références

GPU 1: NVIDIA GeForce RTX 3070
GPU 2: NVIDIA GeForce GTX 1660 SUPER

PassMark - G3D Mark

GPU 1

GPU 2

22253

12712

PassMark - G2D Mark

GPU 1

GPU 2

999

804

Geekbench - OpenCL

GPU 1

GPU 2

123479

62641

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

453.922

187.131

CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)

GPU 1

GPU 2

5803.174

2548.187

CompuBench 1.5 Desktop - T-Rex (Frames/s)

GPU 1

GPU 2

40.757

15.882

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

182.055

117.673

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

1664.554

901.388

GFXBench 4.0 - Car Chase Offscreen (Frames)

GPU 1

GPU 2

31716

17812

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

13566

3717

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

31930

3351

GFXBench 4.0 - Car Chase Offscreen (Fps)

GPU 1

GPU 2

31716

17812

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

13566

3717

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

31930

3351

3DMark Fire Strike - Graphics Score

GPU 1

GPU 2

3163

1278

Nom	NVIDIA GeForce RTX 3070	NVIDIA GeForce GTX 1660 SUPER
PassMark - G3D Mark	22253	12712
PassMark - G2D Mark	999	804
Geekbench - OpenCL	123479	62641
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	453.922	187.131
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	5803.174	2548.187
CompuBench 1.5 Desktop - T-Rex (Frames/s)	40.757	15.882
CompuBench 1.5 Desktop - Video Composition (Frames/s)	182.055	117.673
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	1664.554	901.388
GFXBench 4.0 - Car Chase Offscreen (Frames)	31716	17812
GFXBench 4.0 - Manhattan (Frames)	13566	3717
GFXBench 4.0 - T-Rex (Frames)	31930	3351
GFXBench 4.0 - Car Chase Offscreen (Fps)	31716	17812
GFXBench 4.0 - Manhattan (Fps)	13566	3717
GFXBench 4.0 - T-Rex (Fps)	31930	3351
3DMark Fire Strike - Graphics Score	3163	1278

Comparer les caractéristiques

	NVIDIA GeForce RTX 3070	NVIDIA GeForce GTX 1660 SUPER
Essentiel
Architecture	Ampere	Turing
Nom de code	GA104	TU116
Date de sortie	1 Sep 2020	29 Oct 2019
Prix de sortie (MSRP)	$499	$229
Position dans l’évaluation de la performance	44	223
Genre	Desktop	Desktop
Infos techniques
Vitesse augmenté	1725 MHz	1785 MHz
Vitesse du noyau	1500 MHz	1530 MHz
Processus de fabrication	8 nm	12 nm
Peak Double Precision (FP64) Performance	317.4 GFLOPS (1:64)	157.1 GFLOPS (1:32)
Peak Half Precision (FP16) Performance	20.31 TFLOPS (1:1)	10.05 TFLOPS (2:1)
Peak Single Precision (FP32) Performance	20.31 TFLOPS	5.027 TFLOPS
Pipelines	5888	1408
Pixel fill rate	165.6 GPixel/s	85.68 GPixel/s
Taux de remplissage de la texture	317.4 GTexel/s	157.1 GTexel/s
Thermal Design Power (TDP)	220 Watt	125 Watt
Compte de transistor	17400 million	6600 million
Sorties et ports de vidéo
Connecteurs d’écran	1x HDMI 2.1, 3x DisplayPort 1.4a	1x DVI, 1x HDMI, 1x DisplayPort
Compatibilité, dimensions et exigences
Facteur de forme	Dual-slot
Hauteur	112 mm (4.4 inches)
Interface	PCIe 4.0 x16	PCIe 3.0 x16
Longeur	242 mm, 9.5 inches	9 inches (229 mm)
Énergie du systeme recommandé (PSU)	550 Watt	350 Watt
Connecteurs d’énergie supplementaires	1x 12-pin	1x 8-pin
Largeur	112 mm, 4.4 inches	Dual-slot
Soutien API
DirectX	12 Ultimate (12_2)	12.1
OpenCL	3.0	1.2
OpenGL	4.6	4.6
Shader Model	6.7	6.4
Vulkan
Mémoire
RAM maximale	8 GB	6 GB
Bande passante de la mémoire	448.0 GB/s	336.0 GB/s
Largeur du bus mémoire	256 bit	192 bit
Vitesse de mémoire	1750 MHz, 14 Gbps effective
Genre de mémoire	GDDR6	GDDR6