GPU DB

Back to All GPUs

GPU Comparison

Side-by-side comparison of specifications and performance

Performance Comparison

NVIDIA GeForce RTX 5080

86%
86%

NVIDIA GeForce RTX 4090

116%
116%
NVIDIA GeForce RTX 4090 is approximately 30% faster

Technical Specifications

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

Graphics Processor

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

Graphics Card

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

Clock Speeds

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

Memory

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

Render Config

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

Theoretical Performance

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

Board Design

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

Graphics Features

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

Comparison Summary

7
Specifications Compared
8
Feature Categories
55
Detailed Features

More Comparisons with NVIDIA GeForce RTX 5080

Compare NVIDIA GeForce RTX 5080 with other GPUs of similar performance

More Comparisons with NVIDIA GeForce RTX 4090

Compare NVIDIA GeForce RTX 4090 with other GPUs of similar performance