GPU DB

Back to All GPUs

GPU Comparison

Side-by-side comparison of specifications and performance

Performance Comparison

NVIDIA GeForce RTX 3090

100%
100%

NVIDIA GeForce RTX 4070 Ti SUPER

112%
112%
NVIDIA GeForce RTX 4070 Ti SUPER is approximately 12% faster

Technical Specifications

SpecificationNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 4070 Ti SUPER
Graphics ProcessorDifferent
GA102
AD103
CoresDifferent
10496
8448
TMUsDifferent
328
264
ROPsDifferent
112
96
Memory SizeDifferent
24 GB
16 GB
Memory Type
GDDR6X
GDDR6X
Bus WidthDifferent
384 bit
256 bit

Graphics Processor

FeatureNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 4070 Ti SUPER
GPU NameDifferent
GA102
AD103
GPU VariantDifferent
GA102-300-A1
AD103-275-A1
ArchitectureDifferent
Ampere
Ada Lovelace
FoundryDifferent
Samsung
TSMC
Process SizeDifferent
8 nm
5 nm
TransistorsDifferent
28,300 million
45,900 million
DensityDifferent
45.1M / mm²
121.1M / mm²
Die SizeDifferent
628 mm²
379 mm²
Chip PackageDifferent
BGA-3328
N/A

Graphics Card

FeatureNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 4070 Ti SUPER
Release DateDifferent
Sep 1st, 2020
Jan 8th, 2024
AvailabilityDifferent
Sep 24th, 2020
Jan 24th, 2024
GenerationDifferent
GeForce 30
GeForce 40
PredecessorDifferent
GeForce 20
GeForce 30
SuccessorDifferent
GeForce 40
GeForce 50
Production
Active
Active
Launch PriceDifferent
1,499 USD
799 USD
Current Price
Amazon/Newegg
Amazon/Newegg
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
ReviewsDifferent
59 in our database
40 in our database

Clock Speeds

FeatureNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 4070 Ti SUPER
Base ClockDifferent
1395 MHz
2340 MHz
Boost ClockDifferent
1695 MHz
2610 MHz
Memory ClockDifferent
1219 MHz19.5 Gbps effective
1313 MHz21 Gbps effective

Memory

FeatureNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 4070 Ti SUPER
Memory SizeDifferent
24 GB
16 GB
Memory Type
GDDR6X
GDDR6X
Memory BusDifferent
384 bit
256 bit
BandwidthDifferent
936.2 GB/s
672.3 GB/s

Render Config

FeatureNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 4070 Ti SUPER
Shading UnitsDifferent
10496
8448
TMUsDifferent
328
264
ROPsDifferent
112
96
SM CountDifferent
82
66
Tensor CoresDifferent
328
264
RT CoresDifferent
82
66
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 CacheDifferent
6 MB
48 MB

Theoretical Performance

FeatureNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 4070 Ti SUPER
Pixel RateDifferent
189.8 GPixel/s
250.6 GPixel/s
Texture RateDifferent
556.0 GTexel/s
689.0 GTexel/s
FP16 (half)Different
35.58 TFLOPS (1:1)
44.10 TFLOPS (1:1)
FP32 (float)Different
35.58 TFLOPS
44.10 TFLOPS
FP64 (double)Different
556.0 GFLOPS (1:64)
689.0 GFLOPS (1:64)

Board Design

FeatureNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 4070 Ti SUPER
Slot Width
Triple-slot
Triple-slot
LengthDifferent
336 mm13.2 inches
310 mm12.2 inches
Height
140 mm5.5 inches
140 mm5.5 inches
Width
61 mm2.4 inches
61 mm2.4 inches
TDPDifferent
350 W
285 W
Suggested PSUDifferent
750 W
600 W
Outputs
1x HDMI 2.13x DisplayPort 1.4a
1x HDMI 2.13x DisplayPort 1.4a
Power ConnectorsDifferent
1x 12-pin
1x 16-pin
Board NumberDifferent
PG132 SKU 10
PG141 SKU 323

Graphics Features

FeatureNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 4070 Ti SUPER
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.3
CUDADifferent
8.6
8.9
Shader Model
6.8
6.8

Comparison Summary

7
Specifications Compared
8
Feature Categories
54
Detailed Features

More Comparisons with NVIDIA GeForce RTX 3090

Compare NVIDIA GeForce RTX 3090 with other GPUs of similar performance

More Comparisons with NVIDIA GeForce RTX 4070 Ti SUPER

Compare NVIDIA GeForce RTX 4070 Ti SUPER with other GPUs of similar performance