Radeon Instinct MI300X vs H100 PCIe 80 GB
AI GPU
We compared a Professional market GPU: 192GB VRAM Radeon Instinct MI300X and a GPU: 80GB VRAM H100 PCIe 80 GB 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 2 months late
Boost Clock has increased by 20% (2100MHz vs 1755MHz)
More VRAM (192GB vs 80GB)
Larger VRAM bandwidth (5171GB/s vs 2.04TB/s)
4864 additional rendering cores
H100 PCIe 80 GB 's Advantages
Lower TDP (350W vs 750W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI300X
+59%
81720
H100 PCIe 80 GB
51220
Graphics Card
Dec 2023
Release Date
Oct 2022
Radeon Instinct
Generation
Server Hopper
Professional
Type
AI GPU
PCIe 5.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1000 MHz
Base Clock
1095 MHz
2100 MHz
Boost Clock
1755 MHz
2525 MHz
Memory Clock
1593 MHz
Memory
192GB
Memory Size
80GB
HBM3
Memory Type
HBM2e
8192bit
Memory Bus
5120bit
5171GB/s
Bandwidth
2.04TB/s
Render Config
304
Compute Units
-
-
SM Count
114
19456
Shading Units
14592
1216
TMUs
456
0
ROPs
24
1216
Tensor Cores
456
16 KB (per CU)
L1 Cache
256 KB (per SM)
16 MB
L2 Cache
50 MB
256 MB
L3 Cache
-
Theoretical Performance
0 MPixel/s
Pixel Rate
42.12 GPixel/s
2554 GTexel/s
Texture Rate
800.3 GTexel/s
653.7 TFLOPS
FP16 (half)
204.9 TFLOPS
81.72 TFLOPS
FP32 (float)
51.22 TFLOPS
81.72 TFLOPS
FP64 (double)
25.61 TFLOPS
Board Design
750W
TDP
350W
1150 W
Suggested PSU
750 W
No outputs
Outputs
No outputs
None
Power Connectors
1x 16-pin
Graphics Processor
Aqua Vanjaram
GPU Name
GH100
CDNA 3.0
Architecture
Hopper
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
153 billion
Transistors
80 billion
1017 mm²
Die Size
814 mm²
Graphics Features
N/A
DirectX
N/A
N/A
OpenGL
N/A
3.0
OpenCL
3.0
N/A
Vulkan
N/A
-
CUDA
9.0
N/A
Shader Model
N/A
