Data Center GPU Max Subsystem vs Radeon Instinct MI300
We compared two Professional market GPUs: 128GB VRAM Data Center GPU Max Subsystem and 128GB VRAM Radeon Instinct MI300 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Data Center GPU Max Subsystem 's Advantages
2304 additional rendering cores
Radeon Instinct MI300 's Advantages
Boost Clock has increased by 6% (1700MHz vs 1600MHz)
Larger VRAM bandwidth (3277GB/s vs 3205GB/s)
Lower TDP (600W vs 2400W)
Score
Benchmark
FP32 (float)
Data Center GPU Max Subsystem
+9%
52430
Radeon Instinct MI300
47870
Graphics Card
Jan 2023
Release Date
Jan 2023
Data Center GPU
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
900 MHz
Base Clock
1000 MHz
1600 MHz
Boost Clock
1700 MHz
1565 MHz
Memory Clock
1600 MHz
Memory
128GB
Memory Size
128GB
HBM2e
Memory Type
HBM3
8192bit
Memory Bus
8192bit
3205GB/s
Bandwidth
3277GB/s
Render Config
-
Compute Units
220
16384
Shading Units
14080
1024
TMUs
880
0
ROPs
0
1024
Tensor Cores
880
128
RT Cores
-
64 KB (per EU)
L1 Cache
16 KB (per CU)
408 MB
L2 Cache
16 MB
Theoretical Performance
0 MPixel/s
Pixel Rate
0 MPixel/s
1638 GTexel/s
Texture Rate
1496 GTexel/s
52.43 TFLOPS
FP16 (half)
383.0 TFLOPS
52.43 TFLOPS
FP32 (float)
47.87 TFLOPS
52.43 TFLOPS
FP64 (double)
47.87 TFLOPS
Board Design
2400W
TDP
600W
2800 W
Suggested PSU
1000 W
No outputs
Outputs
No outputs
1x 16-pin
Power Connectors
2x 8-pin
Graphics Processor
Ponte Vecchio
GPU Name
Aqua Vanjaram
Generation 12.5
Architecture
CDNA 3.0
Intel
Foundry
TSMC
10 nm
Process Size
5 nm
100 billion
Transistors
153 billion
1280 mm²
Die Size
1017 mm²
Graphics Features
12 (12_1)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
N/A
Vulkan
N/A
6.6
Shader Model
N/A
