Intel Data Center GPU Flex 140 vs NVIDIA RTX PRO 4000 Blackwell Embedded
GPU Specs Compare
Graphics Card
Release Date
Aug 2022
Unknown
Generation
Data Center GPU
Blackwell-MW
Type
Professional
Mobile
Bus Interface
PCIe 4.0 x8
PCIe 5.0 x16
Clock Speeds
Base Clock
1600 MHz
975 MHz
Boost Clock
1950 MHz
1702 MHz
Memory Clock
1937 MHz
1750 MHz
Memory
Memory Size
6GB
16GB
Memory Type
GDDR6
GDDR7
Memory Bus
96bit
256bit
Bandwidth
186.0GB/s
896.0GB/s
Render Config
Shading Units
1024
7680
TMUs
64
240
ROPs
32
96
RT Cores
8
60
L2 Cache
4 MB
64 MB
SM Count
-
60
Tensor Cores
-
240
L1 Cache
-
128 KB (per SM)
Theoretical Performance
Pixel Rate
62.40 GPixel/s
163.4 GPixel/s
Texture Rate
124.8 GTexel/s
408.5 GTexel/s
FP16 (half)
7.987 TFLOPS
26.14 TFLOPS
FP32 (float)
3.994 TFLOPS
26.14 TFLOPS
FP64 (double)
-
408.5 GFLOPS
Graphics Processor
GPU Name
DG2-128
GB203
GPU Variant
ACM-G11
-
Architecture
Generation 12.7
Blackwell 2.0
Foundry
TSMC
TSMC
Process Size
6 nm
5 nm
Transistors
7.2 billion
45.6 billion
Die Size
157 mm²
378 mm²
Board Design
TDP
75W
80W
Suggested PSU
250 W
-
Outputs
1x HDMI 2.13x DisplayPort 2.0
Portable Device Dependent
Power Connectors
1x 8-pin
None
Graphics Features
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.4
Shader Model
6.6
6.8
CUDA
-
12.0