NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 4090
We compared two Desktop platform GPUs: 24GB VRAM GeForce RTX 3090 Ti and 24GB VRAM GeForce RTX 4090 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 4090 's Advantages
Released 8 months late
Boost Clock has increased by 35% (2520MHz vs 1860MHz)
Larger VRAM bandwidth (1.01TB/s vs 1008GB/s)
5632 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 3090 Ti
40 TFLOPS
GeForce RTX 4090
+106%
82.58 TFLOPS
3DMark Time Spy
GeForce RTX 3090 Ti
21832
GeForce RTX 4090
+66%
36328
3DMark Time Spy Extreme
GeForce RTX 3090 Ti
11318
GeForce RTX 4090
+71%
19460
3DMark Speed Way
GeForce RTX 3090 Ti
5903
GeForce RTX 4090
+70%
10074
Blender
GeForce RTX 3090 Ti
6217
GeForce RTX 4090
+102%
12586
OctaneBench
GeForce RTX 3090 Ti
649
GeForce RTX 4090
+96%
1274
Shadow of the Tomb Raider 2160p
GeForce RTX 3090 Ti
105
GeForce RTX 4090
+76%
185
Shadow of the Tomb Raider 1440p
GeForce RTX 3090 Ti
167
GeForce RTX 4090
+67%
280
Shadow of the Tomb Raider 1080p
GeForce RTX 3090 Ti
210
GeForce RTX 4090
+44%
304
Cyberpunk 2077 2160p
GeForce RTX 3090 Ti
70
GeForce RTX 4090
+34%
94
Cyberpunk 2077 1440p
GeForce RTX 3090 Ti
87
GeForce RTX 4090
+112%
185
Cyberpunk 2077 1080p
GeForce RTX 3090 Ti
125
GeForce RTX 4090
+56%
195
Battlefield 5 2160p
GeForce RTX 3090 Ti
128
GeForce RTX 4090
+45%
186
Battlefield 5 1440p
GeForce RTX 3090 Ti
201
GeForce RTX 4090
203
Battlefield 5 1080p
GeForce RTX 3090 Ti
200
GeForce RTX 4090
+6%
213
GTA 5 2160p
GeForce RTX 3090 Ti
141
GeForce RTX 4090
+17%
165
GTA 5 1440p
GeForce RTX 3090 Ti
+1%
187
GeForce RTX 4090
185
GTA 5 1080p
GeForce RTX 3090 Ti
+21%
226
GeForce RTX 4090
186
Horizon Forbidden West 1080p
GeForce RTX 3090 Ti
114
GeForce RTX 4090
+39%
159
Horizon Forbidden West 1440p
GeForce RTX 3090 Ti
93
GeForce RTX 4090
+45%
135
Horizon Forbidden West 2160p
GeForce RTX 3090 Ti
62
GeForce RTX 4090
+48%
92
Graphics Card
Jan 2022
Release Date
Sep 2022
GeForce 30
Generation
GeForce 40
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1560 MHz
Base Clock
2235 MHz
1860 MHz
Boost Clock
2520 MHz
1313 MHz
Memory Clock
1313 MHz
Memory
24GB
Memory Size
24GB
GDDR6X
Memory Type
GDDR6X
384bit
Memory Bus
384bit
1008GB/s
Bandwidth
1.01TB/s
Render Config
-
-
-
84
SM Count
128
10752
Shading Units
16384
336
TMUs
512
112
ROPs
176
336
Tensor Cores
512
84
RT Cores
128
128 KB (per SM)
L1 Cache
128 KB (per SM)
6 MB
L2 Cache
72 MB
-
-
-
Theoretical Performance
208.3 GPixel/s
Pixel Rate
443.5 GPixel/s
625.0 GTexel/s
Texture Rate
1290 GTexel/s
40.00 TFLOPS
FP16 (half)
82.58 TFLOPS
40.00 TFLOPS
FP32 (float)
82.58 TFLOPS
625.0 GFLOPS
FP64 (double)
1290 GFLOPS
Board Design
450W
TDP
450W
850 W
Suggested PSU
850 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 16-pin
Power Connectors
1x 16-pin
Graphics Processor
GA102
GPU Name
AD102
GA102-350-A1
GPU Variant
AD102-300-A1
Ampere
Architecture
Ada Lovelace
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
28.3 billion
Transistors
76.3 billion
628 mm²
Die Size
609 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.6
CUDA
8.9
6.6
Shader Model
6.8
