NVIDIA Jetson Orin NX 8 GB vs Intel Data Center GPU Flex 170
We compared two Professional market GPUs: 8GB VRAM Jetson Orin NX 8 GB and 16GB VRAM Data Center GPU Flex 170 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Jetson Orin NX 8 GB 's Advantages
Released 7 months late
Lower TDP (20W vs 150W)
Intel Data Center GPU Flex 170 's Advantages
Boost Clock2050MHz
More VRAM (16GB vs 8GB)
Larger VRAM bandwidth (512.0GB/s vs 102.4GB/s)
3072 additional rendering cores
Score
Benchmark
FP32 (float)
Jetson Orin NX 8 GB
1.567 TFLOPS
Data Center GPU Flex 170
+971%
16.79 TFLOPS
Graphics Card
Mar 2023
Release Date
Aug 2022
Tegra
Generation
Data Center GPU
Professional
Type
Professional
PCIe 4.0 x4
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
1950 MHz
-
Boost Clock
2050 MHz
1600 MHz
Memory Clock
2000 MHz
Memory
8GB
Memory Size
16GB
LPDDR5
Memory Type
GDDR6
128bit
Memory Bus
256bit
102.4GB/s
Bandwidth
512.0GB/s
Render Config
-
-
-
8
SM Count
-
1024
Shading Units
4096
32
TMUs
256
16
ROPs
128
32
Tensor Cores
-
-
RT Cores
32
128 KB (per SM)
L1 Cache
-
256 KB
L2 Cache
16 MB
-
-
-
Theoretical Performance
12.24 GPixel/s
Pixel Rate
262.4 GPixel/s
24.48 GTexel/s
Texture Rate
524.8 GTexel/s
3.133 TFLOPS
FP16 (half)
33.59 TFLOPS
1.567 TFLOPS
FP32 (float)
16.79 TFLOPS
783.4 GFLOPS
FP64 (double)
-
Board Design
20W
TDP
150W
-
Suggested PSU
450 W
Portable Device Dependent
Outputs
1x HDMI 2.1
3x DisplayPort 2.0
-
Power Connectors
1x 8-pin
Graphics Processor
GA10B
GPU Name
DG2-512
TE980M-A1
GPU Variant
ACM-G10
Ampere
Architecture
Generation 12.7
Samsung
Foundry
TSMC
8 nm
Process Size
6 nm
Unknown
Transistors
21.7 billion
Unknown
Die Size
406 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.6
CUDA
-
6.7
Shader Model
6.6
