NVIDIA CMP 170HX vs Moore Threads MTT S4000
We compared two Desktop platform GPUs: 16GB VRAM CMP 170HX and 48GB VRAM Moore Threads MTT S4000 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 170HX 's Advantages
Boost Clock1410MHz
Larger VRAM bandwidth (1493GB/s vs 768.0GB/s)
Lower TDP (250W vs 450W)
Moore Threads MTT S4000 's Advantages
More VRAM (48GB vs 16GB)
3712 additional rendering cores
Score
Benchmark
FP32 (float)
CMP 170HX
12.63 TFLOPS
Moore Threads MTT S4000
+94%
24.58 TFLOPS
Graphics Card
Sep 2021
Release Date
Unknown
Mining GPUs
Generation
MUSA-Chunxiao
Desktop
Type
Desktop
PCIe 4.0 x4
Bus Interface
PCIe 5.0 x16
Clock Speeds
1140 MHz
Base Clock
1500 MHz
1410 MHz
Boost Clock
-
1458 MHz
Memory Clock
2000 MHz
Memory
16GB
Memory Size
48GB
HBM2e
Memory Type
GDDR6
4096bit
Memory Bus
384bit
1493GB/s
Bandwidth
768.0GB/s
Render Config
-
Compute Units
64
70
SM Count
-
4480
Shading Units
8192
280
TMUs
512
128
ROPs
512
280
Tensor Cores
128
-
-
-
192 KB (per SM)
L1 Cache
-
8 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
180.5 GPixel/s
Pixel Rate
768.0 GPixel/s
394.8 GTexel/s
Texture Rate
768.0 GTexel/s
50.53 TFLOPS
FP16 (half)
49.15 TFLOPS
12.63 TFLOPS
FP32 (float)
24.58 TFLOPS
6.317 TFLOPS
FP64 (double)
384.0 GFLOPS
Board Design
250W
TDP
450W
600 W
Suggested PSU
850 W
No outputs
Outputs
4x DisplayPort 1.4a
2x 8-pin
Power Connectors
2x 8-pin
Graphics Processor
GA100
GPU Name
MTT Gen 2
GA100-105F-A1
GPU Variant
-
Ampere
Architecture
MUSA-Chunxiao
TSMC
Foundry
TSMC
7 nm
Process Size
12 nm
54.2 billion
Transistors
22 billion
826 mm²
Die Size
Unknown
Graphics Features
N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.4
8.0
CUDA
-
N/A
Shader Model
6.5
