NVIDIA CMP 30HX vs AMD Radeon Instinct MI355X
We compared two Desktop platform GPUs: 6GB VRAM CMP 30HX and 288GB VRAM Radeon Instinct MI355X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 30HX 's Advantages
Lower TDP (125W vs 1400W)
AMD Radeon Instinct MI355X 's Advantages
Released 3 years and 11 months late
Boost Clock has increased by 18% (2100MHz vs 1785MHz)
More VRAM (288GB vs 6GB)
Larger VRAM bandwidth (8.19TB/s vs 336.0GB/s)
18048 additional rendering cores
Score
Benchmark
FP32 (float)
CMP 30HX
5.027 TFLOPS
Radeon Instinct MI355X
+1525%
81.72 TFLOPS
Graphics Card
Feb 2021
Release Date
Jan 2025
Mining GPUs
Generation
Radeon Instinct
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 5.0 x16
Clock Speeds
1530 MHz
Base Clock
1000 MHz
1785 MHz
Boost Clock
2100 MHz
1750 MHz
Memory Clock
2000 MHz
Memory
6GB
Memory Size
288GB
GDDR6
Memory Type
HBM3e
192bit
Memory Bus
8192bit
336.0GB/s
Bandwidth
8.19TB/s
Render Config
-
Compute Units
304
22
SM Count
-
1408
Shading Units
19456
88
TMUs
1216
48
ROPs
0
-
Tensor Cores
1216
-
-
-
64 KB (per SM)
L1 Cache
16 KB (per CU)
1536 KB
L2 Cache
16 MB
-
L3 Cache
256 MB
Theoretical Performance
85.68 GPixel/s
Pixel Rate
0 MPixel/s
157.1 GTexel/s
Texture Rate
2553.6 GTexel/s
10.05 TFLOPS
FP16 (half)
653.7 TFLOPS
5.027 TFLOPS
FP32 (float)
81.72 TFLOPS
157.1 GFLOPS
FP64 (double)
81.72 TFLOPS
Board Design
125W
TDP
1400W
300 W
Suggested PSU
1800 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
None
Graphics Processor
TU116
GPU Name
Aqua Vanjaram X
TU116-100-A1
GPU Variant
-
Turing
Architecture
CDNA 4.0
TSMC
Foundry
TSMC
12 nm
Process Size
3 nm
6.6 billion
Transistors
153 billion
284 mm²
Die Size
1017 mm²
Graphics Features
12 (12_1)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
7.5
CUDA
-
6.8
Shader Model
N/A
