NVIDIA Jetson Orin NX 8 GB vs AMD Instinct MI300X
We compared two Professional market GPUs: 8GB VRAM Jetson Orin NX 8 GB and 192GB VRAM AMD Instinct MI300X 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
Lower TDP (20W vs 750W)
AMD Instinct MI300X 's Advantages
Released 9 months late
Boost Clock2100MHz
More VRAM (192GB vs 8GB)
Larger VRAM bandwidth (5300GB/s vs 102.4GB/s)
18432 additional rendering cores
Score
Benchmark
FP32 (float)
Jetson Orin NX 8 GB
1.567 TFLOPS
AMD Instinct MI300X
+10327%
163.4 TFLOPS
Graphics Card
Mar 2023
Release Date
Dec 2023
Tegra
Generation
Instinct
Professional
Type
Professional
PCIe 4.0 x4
Bus Interface
PCIe 5.0 x16
Clock Speeds
-
Base Clock
1000 MHz
-
Boost Clock
2100 MHz
1600 MHz
Memory Clock
5200 MHz
Memory
8GB
Memory Size
192GB
LPDDR5
Memory Type
HBM3
128bit
Memory Bus
8192bit
102.4GB/s
Bandwidth
5300GB/s
Render Config
-
Compute Units
304
8
SM Count
-
1024
Shading Units
19456
32
TMUs
880
16
ROPs
0
32
Tensor Cores
-
-
-
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
256 KB
L2 Cache
16 MB
-
-
-
Theoretical Performance
12.24 GPixel/s
Pixel Rate
0 MPixel/s
24.48 GTexel/s
Texture Rate
1496 GTexel/s
3.133 TFLOPS
FP16 (half)
1300 TFLOPS
1.567 TFLOPS
FP32 (float)
163.4 TFLOPS
783.4 GFLOPS
FP64 (double)
81.7 TFLOPS
Board Design
20W
TDP
750W
-
Suggested PSU
1000 W
Portable Device Dependent
Outputs
No outputs
-
Power Connectors
None
Graphics Processor
GA10B
GPU Name
MI300
TE980M-A1
GPU Variant
-
Ampere
Architecture
CDNA 3.0
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
Unknown
Transistors
146 billion
Unknown
Die Size
1017 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
8.6
CUDA
-
6.7
Shader Model
N/A
