GeForce RTX 5070 vs GeForce RTX 5090 D
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 5070 and 32GB VRAM GeForce RTX 5090 D to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 5070 Advantages
Boost Clock has increased by 4% (2512MHz vs 2407MHz)
Lower TDP (250W vs 575W)
GeForce RTX 5090 D Advantages
More VRAM (32GB vs 12GB)
Larger VRAM bandwidth (1.79TB/s vs 672.0GB/s)
15616 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 5070
30870
GeForce RTX 5090 D
+239%
104800
3DMark Time Spy
GeForce RTX 5070
22544
GeForce RTX 5090 D
+113%
48052
3DMark Time Spy Extreme
GeForce RTX 5070
10789
GeForce RTX 5090 D
+140%
25999
3DMark Speed Way
GeForce RTX 5070
5896
GeForce RTX 5090 D
+150%
14790
Graphics Card
Mar 2025
Release Date
Jan 2025
GeForce 50
Generation
GeForce 50
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
2325 MHz
Base Clock
2017 MHz
2512 MHz
Boost Clock
2407 MHz
1750 MHz
Memory Clock
1750 MHz
Memory
12GB
Memory Size
32GB
GDDR7
Memory Type
GDDR7
192bit
Memory Bus
512bit
672.0GB/s
Bandwidth
1.79TB/s
Render Config
48
SM Count
170
6144
Shading Units
21760
192
TMUs
680
80
ROPs
176
192
Tensor Cores
680
48
RT Cores
170
128 KB (per SM)
L1 Cache
128 KB (per SM)
48 MB
L2 Cache
96 MB
Theoretical Performance
201.0 GPixel/s
Pixel Rate
423.6 GPixel/s
482.3 GTexel/s
Texture Rate
1637 GTexel/s
30.87 TFLOPS
FP16 (half)
104.8 TFLOPS
30.87 TFLOPS
FP32 (float)
104.8 TFLOPS
482.3 GFLOPS
FP64 (double)
1.637 TFLOPS
Board Design
250W
TDP
575W
600 W
Suggested PSU
950 W
1x HDMI 2.1b
3x DisplayPort 2.1b
3x DisplayPort 2.1b
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1b
3x DisplayPort 2.1b
1x 16-pin
Power Connectors
1x 16-pin
Graphics Processor
GB205
GPU Name
GB202
GB205-300-A1
GPU Variant
-
Blackwell 2.0
Architecture
Blackwell 2.0
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
31.1 billion
Transistors
92.2 billion
263 mm²
Die Size
750 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.4
Vulkan
1.4
10.1
CUDA
10.1
6.8
Shader Model
6.8
