NVIDIA RTX PRO 4000 Blackwell vs Intel Data Center GPU Max Subsystem

GPU Specs Compare

Graphics Card

Release Date
Mar 2025
Jan 2023
Generation
Blackwell PRO W
Data Center GPU
Type
Desktop
Professional
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16

Clock Speeds

Base Clock
1230 MHz
900 MHz
Boost Clock
2055 MHz
1600 MHz
Memory Clock
1750 MHz
1565 MHz

Memory

Memory Size
24GB
128GB
Memory Type
GDDR7
HBM2e
Memory Bus
192bit
8192bit
Bandwidth
672.0GB/s
3205GB/s

Render Config

SM Count
70
-
Shading Units
8960
16384
TMUs
280
1024
ROPs
96
0
Tensor Cores
280
1024
RT Cores
70
128
L1 Cache
128 KB (per SM)
64 KB (per EU)
L2 Cache
48 MB
408 MB

Theoretical Performance

Pixel Rate
197.3 GPixel/s
0 MPixel/s
Texture Rate
575.4 GTexel/s
1638 GTexel/s
FP16 (half)
36.83 TFLOPS
52.43 TFLOPS
FP32 (float)
36.83 TFLOPS
52.43 TFLOPS
FP64 (double)
575.4 GFLOPS
52.43 TFLOPS

Graphics Processor

GPU Name
GB203
Ponte Vecchio
Architecture
Blackwell 2.0
Generation 12.5
Foundry
TSMC
Intel
Process Size
5 nm
10 nm
Transistors
45.6 billion
100 billion
Die Size
378 mm²
1280 mm²

Board Design

TDP
140W
2400W
Suggested PSU
300 W
2800 W
Outputs
4x DisplayPort 2.1b
No outputs
Power Connectors
1x 16-pin
1x 16-pin

Graphics Features

DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.4
N/A
CUDA
12.0
-
Shader Model
6.8
6.6