GPU DB

Back to All GPUs

GPU Comparison

Side-by-side comparison of specifications and performance

Performance Comparison

NVIDIA GeForce RTX 4090

116%
116%

NVIDIA GeForce RTX 5080

86%
86%
NVIDIA GeForce RTX 4090 is approximately 30% faster

Technical Specifications

SpecificationNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5080
Graphics ProcessorDifferent
AD102
GB203
CoresDifferent
16384
10752
TMUsDifferent
512
336
ROPsDifferent
176
112
Memory SizeDifferent
24 GB
16 GB
Memory TypeDifferent
GDDR6X
GDDR7
Bus WidthDifferent
384 bit
256 bit

Graphics Processor

FeatureNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5080
GPU NameDifferent
AD102
GB203
GPU VariantDifferent
AD102-300-A1
GB203-400-A1
ArchitectureDifferent
Ada Lovelace
Blackwell 2.0
Foundry
TSMC
TSMC
Process Size
5 nm
5 nm
TransistorsDifferent
76,300 million
45,600 million
DensityDifferent
125.3M / mm²
120.6M / mm²
Die SizeDifferent
609 mm²
378 mm²
Process TypeDifferent
N/A
4N FinFET

Graphics Card

FeatureNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5080
Release DateDifferent
Sep 20th, 2022
Jan 30th, 2025
AvailabilityDifferent
Oct 12th, 2022
N/A
GenerationDifferent
GeForce 40
GeForce 50
PredecessorDifferent
GeForce 30
GeForce 40
SuccessorDifferent
GeForce 50
N/A
Production
Active
Active
Launch PriceDifferent
1,599 USD
999 USD
Current PriceDifferent
Amazon/Newegg
N/A
Bus InterfaceDifferent
PCIe 4.0 x16
PCIe 5.0 x16
ReviewsDifferent
76 in our database
72 in our database
AnnouncedDifferent
N/A
Jan 6th, 2025

Clock Speeds

FeatureNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5080
Base ClockDifferent
2235 MHz
2295 MHz
Boost ClockDifferent
2520 MHz
2617 MHz
Memory ClockDifferent
1313 MHz21 Gbps effective
1875 MHz30 Gbps effective

Memory

FeatureNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5080
Memory SizeDifferent
24 GB
16 GB
Memory TypeDifferent
GDDR6X
GDDR7
Memory BusDifferent
384 bit
256 bit
BandwidthDifferent
1.01 TB/s
960.0 GB/s

Render Config

FeatureNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5080
Shading UnitsDifferent
16384
10752
TMUsDifferent
512
336
ROPsDifferent
176
112
SM CountDifferent
128
84
Tensor CoresDifferent
512
336
RT CoresDifferent
128
84
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 CacheDifferent
72 MB
64 MB

Theoretical Performance

FeatureNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5080
Pixel RateDifferent
443.5 GPixel/s
293.1 GPixel/s
Texture RateDifferent
1,290.2 GTexel/s
879.3 GTexel/s
FP16 (half)Different
82.58 TFLOPS (1:1)
56.28 TFLOPS (1:1)
FP32 (float)Different
82.58 TFLOPS
56.28 TFLOPS
FP64 (double)Different
1,290.2 GFLOPS (1:64)
879.3 GFLOPS (1:64)

Board Design

FeatureNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5080
Slot WidthDifferent
Triple-slot
Dual-slot
Length
304 mm12 inches
304 mm12 inches
Height
137 mm5.4 inches
137 mm5.4 inches
WidthDifferent
61 mm2.4 inches
40 mm1.6 inches
TDPDifferent
450 W
360 W
Suggested PSUDifferent
850 W
750 W
OutputsDifferent
1x HDMI 2.13x DisplayPort 1.4a
1x HDMI 2.1b3x DisplayPort 2.1b
Power Connectors
1x 16-pin
1x 16-pin
Board NumberDifferent
PG139 SKU 330
PG147 SKU 45

Graphics Features

FeatureNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 5080
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
VulkanDifferent
1.3
1.4
CUDADifferent
8.9
12.0
Shader Model
6.8
6.8

Comparison Summary

7
Specifications Compared
8
Feature Categories
55
Detailed Features

More Comparisons with NVIDIA GeForce RTX 4090

Compare NVIDIA GeForce RTX 4090 with other GPUs of similar performance

More Comparisons with NVIDIA GeForce RTX 5080

Compare NVIDIA GeForce RTX 5080 with other GPUs of similar performance