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