NVIDIA RTX PRO 4000 Blackwell vs NVIDIA GeForce RTX 5070
GPU Specs Compare
Graphics Card
Release Date
Mar 2025
Mar 2025
Generation
Blackwell PRO W
GeForce 50
Type
Desktop
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1230 MHz
2325 MHz
Boost Clock
2055 MHz
2512 MHz
Memory Clock
1750 MHz
1750 MHz
Memory
Memory Size
24GB
12GB
Memory Type
GDDR7
GDDR7
Memory Bus
192bit
192bit
Bandwidth
672.0GB/s
672.0GB/s
Render Config
SM Count
70
48
Shading Units
8960
6144
TMUs
280
192
ROPs
96
80
Tensor Cores
280
192
RT Cores
70
48
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
48 MB
48 MB
Theoretical Performance
Pixel Rate
197.3 GPixel/s
201.0 GPixel/s
Texture Rate
575.4 GTexel/s
482.3 GTexel/s
FP16 (half)
36.83 TFLOPS
30.87 TFLOPS
FP32 (float)
36.83 TFLOPS
30.87 TFLOPS
FP64 (double)
575.4 GFLOPS
482.3 GFLOPS
Graphics Processor
GPU Name
GB203
GB205
Architecture
Blackwell 2.0
Blackwell 2.0
Foundry
TSMC
TSMC
Process Size
5 nm
5 nm
Transistors
45.6 billion
31.1 billion
Die Size
378 mm²
263 mm²
GPU Variant
-
GB205-300-A1
Board Design
TDP
140W
250W
Suggested PSU
300 W
600 W
Outputs
4x DisplayPort 2.1b
1x HDMI 2.1b3x DisplayPort 2.1b
Power Connectors
1x 16-pin
1x 16-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.4
1.4
CUDA
12.0
12.0
Shader Model
6.8
6.8
📊 Benchmark
3DMark Time Spy
-
22,544
3DMark Time Spy Extreme
-
10,789
3DMark Speed Way
-
5,896
Blender
-
6,218