GeForce RTX 3070 vs GeForce RTX 4090 D
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3070 and 24GB VRAM GeForce RTX 4090 D to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3070 's Advantages
Lower TDP (220W vs 425W)
GeForce RTX 4090 D 's Advantages
Released 3 years and 3 months late
Boost Clock has increased by 46% (2520MHz vs 1725MHz)
More VRAM (24GB vs 8GB)
Larger VRAM bandwidth (1008GB/s vs 448.0GB/s)
8704 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 3070
20310
GeForce RTX 4090 D
+262%
73540
3DMark Time Spy
GeForce RTX 3070
13641
GeForce RTX 4090 D
+151%
34258
3DMark Time Spy Extreme
GeForce RTX 3070
6762
GeForce RTX 4090 D
+164%
17914
3DMark Speed Way
GeForce RTX 3070
3453
GeForce RTX 4090 D
+181%
9719
Graphics Card
Sep 2020
Release Date
Dec 2023
GeForce 30
Generation
GeForce 40
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1500 MHz
Base Clock
2280 MHz
1725 MHz
Boost Clock
2520 MHz
1750 MHz
Memory Clock
1313 MHz
Memory
8GB
Memory Size
24GB
GDDR6
Memory Type
GDDR6X
256bit
Memory Bus
384bit
448.0GB/s
Bandwidth
1008GB/s
Render Config
46
SM Count
114
5888
Shading Units
14592
184
TMUs
456
96
ROPs
176
184
Tensor Cores
456
46
RT Cores
114
128 KB (per SM)
L1 Cache
128 KB (per SM)
4 MB
L2 Cache
72 MB
Theoretical Performance
165.6 GPixel/s
Pixel Rate
443.5 GPixel/s
317.4 GTexel/s
Texture Rate
1149 GTexel/s
20.31 TFLOPS
FP16 (half)
73.54 TFLOPS
20.31 TFLOPS
FP32 (float)
73.54 TFLOPS
317.4 GFLOPS
FP64 (double)
1149 GFLOPS
Board Design
220W
TDP
425W
550 W
Suggested PSU
800 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 12-pin
Power Connectors
1x 16-pin
Graphics Processor
GA104
GPU Name
AD102
GA104-300-A1
GPU Variant
AD102-250-A1
Ampere
Architecture
Ada Lovelace
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
17.4 billion
Transistors
76.3 billion
392 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
6.7
