Radeon Instinct MI300X vs Data Center GPU Flex 170
We compared two Professional market GPUs: 192GB VRAM Radeon Instinct MI300X 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
Radeon Instinct MI300X 's Advantages
Released 1 years and 4 months late
Boost Clock has increased by 2% (2100MHz vs 2050MHz)
More VRAM (192GB vs 16GB)
Larger VRAM bandwidth (5171GB/s vs 512.0GB/s)
15360 additional rendering cores
Data Center GPU Flex 170 's Advantages
Lower TDP (150W vs 750W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI300X
+386%
81720
Data Center GPU Flex 170
16790
Graphics Card
Dec 2023
Release Date
Aug 2022
Radeon Instinct
Generation
Data Center GPU
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1000 MHz
Base Clock
1950 MHz
2100 MHz
Boost Clock
2050 MHz
2525 MHz
Memory Clock
2000 MHz
Memory
192GB
Memory Size
16GB
HBM3
Memory Type
GDDR6
8192bit
Memory Bus
256bit
5171GB/s
Bandwidth
512.0GB/s
Render Config
304
Compute Units
-
19456
Shading Units
4096
1216
TMUs
256
0
ROPs
128
1216
Tensor Cores
-
-
RT Cores
32
16 KB (per CU)
L1 Cache
-
16 MB
L2 Cache
16 MB
256 MB
L3 Cache
-
Theoretical Performance
0 MPixel/s
Pixel Rate
262.4 GPixel/s
2554 GTexel/s
Texture Rate
524.8 GTexel/s
653.7 TFLOPS
FP16 (half)
33.59 TFLOPS
81.72 TFLOPS
FP32 (float)
16.79 TFLOPS
81.72 TFLOPS
FP64 (double)
-
Board Design
750W
TDP
150W
1150 W
Suggested PSU
450 W
No outputs
Outputs
1x HDMI 2.1
3x DisplayPort 2.0
None
Power Connectors
1x 8-pin
Graphics Processor
Aqua Vanjaram
GPU Name
DG2-512
-
GPU Variant
ACM-G10
CDNA 3.0
Architecture
Generation 12.7
TSMC
Foundry
TSMC
5 nm
Process Size
6 nm
153 billion
Transistors
21.7 billion
1017 mm²
Die Size
406 mm²
Graphics Features
N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
N/A
Shader Model
6.6
