NVIDIA CMP 170HX vs NVIDIA CMP 30HX
We compared two Desktop platform GPUs: 16GB VRAM CMP 170HX and 6GB VRAM CMP 30HX to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 170HX 's Advantages
Released 7 months late
More VRAM (16GB vs 6GB)
Larger VRAM bandwidth (1493GB/s vs 336.0GB/s)
3072 additional rendering cores
NVIDIA CMP 30HX 's Advantages
Boost Clock has increased by 27% (1785MHz vs 1410MHz)
Lower TDP (125W vs 250W)
Score
Benchmark
FP32 (float)
CMP 170HX
+151%
12.63 TFLOPS
CMP 30HX
5.027 TFLOPS
Graphics Card
Sep 2021
Release Date
Feb 2021
Mining GPUs
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 4.0 x4
Bus Interface
PCIe 1.0 x4
Clock Speeds
1140 MHz
Base Clock
1530 MHz
1410 MHz
Boost Clock
1785 MHz
1458 MHz
Memory Clock
1750 MHz
Memory
16GB
Memory Size
6GB
HBM2e
Memory Type
GDDR6
4096bit
Memory Bus
192bit
1493GB/s
Bandwidth
336.0GB/s
Render Config
-
-
-
70
SM Count
22
4480
Shading Units
1408
280
TMUs
88
128
ROPs
48
280
Tensor Cores
-
-
-
-
192 KB (per SM)
L1 Cache
64 KB (per SM)
8 MB
L2 Cache
1536 KB
-
-
-
Theoretical Performance
180.5 GPixel/s
Pixel Rate
85.68 GPixel/s
394.8 GTexel/s
Texture Rate
157.1 GTexel/s
50.53 TFLOPS
FP16 (half)
10.05 TFLOPS
12.63 TFLOPS
FP32 (float)
5.027 TFLOPS
6.317 TFLOPS
FP64 (double)
157.1 GFLOPS
Board Design
250W
TDP
125W
600 W
Suggested PSU
300 W
No outputs
Outputs
No outputs
2x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
GA100
GPU Name
TU116
GA100-105F-A1
GPU Variant
TU116-100-A1
Ampere
Architecture
Turing
TSMC
Foundry
TSMC
7 nm
Process Size
12 nm
54.2 billion
Transistors
6.6 billion
826 mm²
Die Size
284 mm²
Graphics Features
N/A
DirectX
12 (12_1)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
8.0
CUDA
7.5
N/A
Shader Model
6.8
