NVIDIA Jetson Orin NX 16 GB vs AMD Radeon Instinct MI8
We compared two Professional market GPUs: 16GB VRAM Jetson Orin NX 16 GB and 4GB VRAM Radeon Instinct MI8 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Jetson Orin NX 16 GB 's Advantages
Released 6 years and 2 months late
More VRAM (16GB vs 4GB)
Lower TDP (25W vs 175W)
AMD Radeon Instinct MI8 's Advantages
Larger VRAM bandwidth (512.0GB/s vs 102.4GB/s)
3072 additional rendering cores
Score
Benchmark
FP32 (float)
Jetson Orin NX 16 GB
1.88 TFLOPS
Radeon Instinct MI8
+335%
8.192 TFLOPS
Graphics Card
Feb 2023
Release Date
Dec 2016
Tegra
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 4.0 x4
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
-
-
-
-
-
1600 MHz
Memory Clock
500 MHz
Memory
16GB
Memory Size
4GB
LPDDR5
Memory Type
HBM
128bit
Memory Bus
4096bit
102.4GB/s
Bandwidth
512.0GB/s
Render Config
-
Compute Units
64
8
SM Count
-
1024
Shading Units
4096
32
TMUs
256
16
ROPs
64
32
Tensor Cores
-
-
-
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
256 KB
L2 Cache
2 MB
-
-
-
Theoretical Performance
14.69 GPixel/s
Pixel Rate
64.00 GPixel/s
29.38 GTexel/s
Texture Rate
256.0 GTexel/s
3.760 TFLOPS
FP16 (half)
8.192 TFLOPS
1.880 TFLOPS
FP32 (float)
8.192 TFLOPS
940.0 GFLOPS
FP64 (double)
512.0 GFLOPS
Board Design
25W
TDP
175W
-
Suggested PSU
450 W
Portable Device Dependent
Outputs
No outputs
-
Power Connectors
1x 8-pin
Graphics Processor
GA10B
GPU Name
Fiji
TE980M-A1
GPU Variant
Fiji XT CA
(215-0862120)
Ampere
Architecture
GCN 3.0
Samsung
Foundry
TSMC
8 nm
Process Size
28 nm
Unknown
Transistors
8.9 billion
Unknown
Die Size
596 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2.170
8.6
CUDA
-
6.7
Shader Model
6.5
