NVIDIA GeForce RTX 3090 vs AMD Radeon RX 7600

VS

NVIDIA GeForce RTX 3090

AMD Radeon RX 7600

We compared two Desktop platform GPUs: 24GB VRAM GeForce RTX 3090 and 8GB VRAM Radeon RX 7600 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce RTX 3090 's Advantages

More VRAM (24GB vs 8GB)

Larger VRAM bandwidth (936.2GB/s vs 288.0GB/s)

8448 additional rendering cores

AMD Radeon RX 7600 's Advantages

Released 2 years and 8 months late

Boost Clock has increased by 57% (2655MHz vs 1695MHz)

Lower TDP (165W vs 350W)

Score

Benchmark

FP32 (float)

GeForce RTX 3090 +63%

35.58 TFLOPS

Radeon RX 7600

21.75 TFLOPS

3DMark Time Spy

GeForce RTX 3090 +81%

19948

Radeon RX 7600

11014

Shadow of the Tomb Raider 2160p

GeForce RTX 3090 +144%

93

Radeon RX 7600

38

Shadow of the Tomb Raider 1440p

GeForce RTX 3090 +79%

154

Radeon RX 7600

86

Shadow of the Tomb Raider 1080p

GeForce RTX 3090 +53%

200

Radeon RX 7600

130

Cyberpunk 2077 2160p

GeForce RTX 3090 +230%

66

Radeon RX 7600

20

Cyberpunk 2077 1440p

GeForce RTX 3090 +64%

79

Radeon RX 7600

48

Cyberpunk 2077 1080p

GeForce RTX 3090 +58%

114

Radeon RX 7600

72

GTA 5 2160p

GeForce RTX 3090 +59%

131

Radeon RX 7600

82

GTA 5 1440p

GeForce RTX 3090 +121%

182

Radeon RX 7600

82

GTA 5 1080p

GeForce RTX 3090 +10%

209

Radeon RX 7600

190

Horizon Forbidden West 1080p

GeForce RTX 3090 +64%

105

Radeon RX 7600

64

Horizon Forbidden West 1440p

GeForce RTX 3090 +89%

91

Radeon RX 7600

48

Horizon Forbidden West 2160p

GeForce RTX 3090 +100%

56

Radeon RX 7600

28

GeForce RTX 3090

VS

Radeon RX 7600

Graphics Card

Sep 2020

Release Date

May 2023

GeForce 30

Generation

Navi III

Desktop

Type

Desktop

PCIe 4.0 x16

Bus Interface

PCIe 4.0 x8

Clock Speeds

1395 MHz

Base Clock

1720 MHz

1695 MHz

Boost Clock

2655 MHz

1219 MHz

Memory Clock

2250 MHz

Memory

24GB

Memory Size

8GB

GDDR6X

Memory Type

GDDR6

384bit

Memory Bus

128bit

936.2GB/s

Bandwidth

288.0GB/s

Render Config

-

Compute Units

32

82

SM Count

-

10496

Shading Units

2048

328

TMUs

128

112

ROPs

64

328

Tensor Cores

-

82

RT Cores

32

128 KB (per SM)

L1 Cache

128 KB per Array

6 MB

L2 Cache

2 MB

-

L3 Cache

32 MB

Theoretical Performance

189.8 GPixel/s

Pixel Rate

169.9 GPixel/s

556.0 GTexel/s

Texture Rate

339.8 GTexel/s

35.58 TFLOPS

FP16 (half)

43.50 TFLOPS

35.58 TFLOPS

FP32 (float)

21.75 TFLOPS

556.0 GFLOPS

FP64 (double)

679.7 GFLOPS

Board Design

350W

TDP

165W

750 W

Suggested PSU

450 W

1x HDMI 2.1 3x DisplayPort 1.4a

Outputs

1x HDMI 2.1a 3x DisplayPort 2.1

1x 12-pin

Power Connectors

1x 8-pin

Graphics Processor

GA102

GPU Name

Navi 33

GA102-300-A1

GPU Variant

Navi 33 XL

Ampere

Architecture

RDNA 3.0

Samsung

Foundry

TSMC

8 nm

Process Size

6 nm

28.3 billion

Transistors

13.3 billion

628 mm²

Die Size

204 mm²

Graphics Features

12 Ultimate (12_2)

DirectX

12 Ultimate (12_2)

4.6

OpenGL

4.6

3.0

OpenCL

2.2

1.3

Vulkan

1.3

8.6

CUDA

-

6.6

Shader Model

6.7

Related GPU Comparisons

1

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce GT 415 OEM

2

NVIDIA GeForce RTX 3090 vs AMD Radeon Sky 900

3

NVIDIA GeForce RTX 3090 vs ATI FirePro 2460 Multi View

4

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce GTX 960

5

NVIDIA GeForce RTX 3090 vs AMD Radeon HD 6770 Green Edition

6

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce GT 520 PCI

7

NVIDIA GeForce RTX 3090 vs NVIDIA GeForce 6800 XT

8

NVIDIA GeForce RTX 3090 vs MTT S70

9

NVIDIA GeForce RTX 3090 vs AMD Radeon R9 290X

10

NVIDIA GeForce RTX 3090 vs ATI Radeon X1700 FSC

Related News

1

Intel Wildcat Lake Appears on Shipping List with FCBGA1516 Socket, Poised to Replace Alder Lake-N

2

The Commencement of ARM and Qualcomm Licensing Dispute Trial: Potential Major Impact on PC Market

3

NVIDIA Allegedly Equips RTX 5080 with 30Gbps Memory Speed, Other Models to Feature 28Gbps

4

Intel Reports High Return Rates for Devices Featuring Snapdragon X Series; Qualcomm Counters with 'Industry Standard' Claim

5

Intel Confirms Panther Lake Adopts 18A Process, ES0 Samples Already Sent to Customers

6

Complete Lineup of Core Ultra 200HX/H/U and Core 200H/U Revealed: 31 Models to Dazzle the Eyes

7

Amechi Unveils V1 Mini PC: Only 0.33L Volume with 150W Power Consumption

8

iPhone 17 Series Set for Major Design Overhaul: Camera Module Transformed into Sleek Strip

9

The Thinnest iPhone Ever! iPhone 17 Air Reportedly Enters Foxconn's NPI Stage

10

Apple Allegedly Cancels M4 Extreme, Originally Planned for Mac Pro with 64-Core CPU and 160-Core GPU