NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 2070 Super Full Specs

Summary

10,496 Shaders 1.7GHz	2,560 Shaders 1.77GHz
24GB GDDR6X936.2GB/s	8GB GDDR6448GB/s
Peak·FP32·FP16 35.58 TFLOPS	Peak·FP32·FP16 9.06 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 350W	TDP 215W
Power Connectors 1x 12-Pin - -	Power Connectors - 1x 8-Pin 1x 6-Pin

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

GeForce RTX 30901.14 POPSINT4 Tensor Sparse

x3.93

GeForce RTX 2070 Super290 TOPSINT4 Tensor

x1

Show Top Score

Theoretical Performance

Clock Speed1695MHz UC·Base·Boost·OC	Clock Speed1770MHz UC·Base·Boost·OC
Peak OPS 1.14 POPSINT4 Tensor Sparse	Peak OPS 290 TOPSINT4 Tensor
Tensor FP16-16 142.3 TFLOPS FP16-16 Tensor Sparse 284.7 TFLOPS Tensor FP16-32 71.16 TFLOPS FP16-32 Tensor Sparse 142.3 TFLOPS	Tensor FP16-16 72.5 TFLOPS FP16-16 Tensor Sparse - Tensor FP16-32 36.25 TFLOPS FP16-32 Tensor Sparse -
BF16 35.58 TFLOPS Tensor BF16 71.16 TFLOPS BF16 Tensor Sparse 142.3 TFLOPS	BF16 - Tensor BF16 36.25 TFLOPS BF16 Tensor Sparse -
Tensor TF32 35.58 TFLOPS	Tensor TF32 36.25 TFLOPS
FP32 35.58 TFLOPS	FP32 9.06 TFLOPS
FP64 556 GFLOPS	FP64 283.2 GFLOPS
Tensor INT4 569.3 TOPS	Tensor INT4 290 TOPS
Tensor INT8 284.7 TOPS	Tensor INT8 145 TOPS
Ray 53.66 TOPS	Ray 27.34 TOPS
Pixel Rate 189.8 GPixel/s	Pixel Rate 113.3 GPixel/s
Texture Rate 556 GTexel/s	Texture Rate 283.2 GTexel/s

Core Config

Shaders 10,496 Shaders	Shaders 2,560 Shaders
TMUs 328 TMUs	TMUs 160 TMUs
ROPs 112 ROPs	ROPs 64 ROPs
Tensor Cores 328 T-Cores	Tensor Cores 320 T-Cores
RT Cores 82 RT-Cores	RT Cores 40 RT-Cores
SMs 82 SMs	SMs 40 SMs

Clocks

Base Clock 1.4GHz	Base Clock 1.6GHz
Boost Clock 1.7GHz	Boost Clock 1.77GHz

Cache

L2 Cache 6.1MB shared

L2 Cache 4.1MB shared

Memory

24GB GDDR6X	8GB GDDR6
Memory Bus 384-bit	Memory Bus 256-bit
Memory Speed 19.5GT/s	Memory Speed 14GT/s
Memory Bandwidth 936.2GB/s	Memory Bandwidth 448GB/s
ECC No	ECC No

Power & Thermals

TDP 350W	TDP 215W
Max Temp 93°C Max	Max Temp 88°C Max

Video Output

Multi-Monitor 4	Multi-Monitor 4
HDCP HDCP 2.3	HDCP HDCP 2.2

Ports

3x DisplayPort 1.4	3x DisplayPort 1.4
1x HDMI 2.1	-
-	1x HDMI 2.0
-	1x DVI-D Dual-Link
-	1x USB-C

Encoder

Encoder Model NVENC 7

Encoder Model NVENC 7

Decoder

Decoder Model NVDEC 5

Decoder Model NVDEC 4

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe 3-Slots	PCIe 2-Slots
Height 140 mm (5.51") Width 336 mm (13.23") Depth 61 mm (2.4")	Height 115.7 mm (4.55") Width 266.7 mm (10.5") Depth 35 mm (1.38")
Cooling Open-Air 2x Fans	Cooling Open-Air 2x Fans
Power Connectors 1x 12-Pin	Power Connectors 1x 8-Pin, 1x 6-Pin

Chip

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Ampere	Architecture Turing
Family GeForce 30	Family GeForce 20
Branding	Branding
Codename NV172	Codename NV164
Chip Variant GA102-200-KD-A1	Chip Variant TU104-150-KC-A1
Market Segment Desktop	Market Segment Desktop
Release Date Sep 24, 2020	Release Date Jul 9, 2019

Fabrication

Foundry Samsung	Foundry TSMC
Fabrication Node 8N	Fabrication Node 12FFN
Die Size 628mm²	Die Size 545mm²
Transistor Count 28.3 Billion	Transistor Count 13.6 Billion
Transistor Density 45.04 MTr/mm²	Transistor Density 24.95 MTr/mm²

Images

No images available

No images available

Used In

Desktops XPS(XD8950, Late 2021)Aurora(R13, Late 2021)Aurora(R14, Late 2021) Show 5 more

Desktops -

Competitors

NVIDIAGeForce RTX 3090 vs GPU AMDRadeon RX 9070 XT NVIDIAGeForce RTX 3090 vs GPU NVIDIAGeForce RTX 5070 Ti NVIDIAGeForce RTX 3090 vs GPU NVIDIAGeForce RTX 4070 Ti Super Show 12 more

NVIDIAGeForce RTX 2070 Super vs GPU AMDRadeon RX 7700 NVIDIAGeForce RTX 2070 Super vs GPU AMDRadeon RX 7700 XT NVIDIAGeForce RTX 2070 Super vs GPU AMDRadeon RX 7600 XT Show 12 more