NVIDIA RTX PRO 4000 Blackwell SFF vs NVIDIA GeForce RTX 2070
GPU · Specs Compare
Graphics Card
Release Date
Aug 2025
Oct 2018
Generation
Blackwell PRO W
GeForce 20
Type
Desktop
Desktop
Bus Interface
PCIe 5.0 x8
PCIe 3.0 x16
Clock Speeds
Base Clock
577 MHz
1410 MHz
Boost Clock
1432 MHz
1620 MHz
Memory Clock
1125 MHz
1750 MHz
Memory
Memory Size
24GB
8GB
Memory Type
GDDR7
GDDR6
Memory Bus
192bit
256bit
Bandwidth
432.0GB/s
448.0GB/s
Render Config
SM Count
70
36
Shading Units
8960
2304
TMUs
280
144
ROPs
96
64
Tensor Cores
280
288
RT Cores
70
36
L1 Cache
128 KB (per SM)
64 KB (per SM)
L2 Cache
48 MB
4 MB
Theoretical Performance
Pixel Rate
137.5 GPixel/s
103.7 GPixel/s
Texture Rate
401.0 GTexel/s
233.3 GTexel/s
FP16 (half)
25.66 TFLOPS
14.93 TFLOPS
FP32 (float)
25.66 TFLOPS
7.465 TFLOPS
FP64 (double)
401.0 GFLOPS
233.3 GFLOPS
Graphics Processor
GPU Name
GB203
TU106
Architecture
Blackwell 2.0
Turing
Foundry
TSMC
TSMC
Process Size
5 nm
12 nm
Transistors
45.6 billion
10.8 billion
Die Size
378 mm²
445 mm²
GPU Variant
—
TU106-400A-A1
Board Design
TDP
70W
175W
Suggested PSU
250 W
450 W
Outputs
4x mini-DisplayPort 2.1b
1x DVI1x HDMI 2.02x DisplayPort 1.4a1x USB Type-C
Power Connectors
None
1x 8-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
1.3
CUDA
12.0
7.5
Shader Model
6.8
6.8
Benchmark
3DMark Time Spy
—
9,088
3DMark Time Spy Extreme
—
4,309
▲ Specs Compare
Data sourced from official specifications and benchmark tests.