Moore Threads MTT S4000 vs NVIDIA CMP 40HX
We compared two Desktop platform GPUs: 48GB VRAM Moore Threads MTT S4000 and 8GB VRAM CMP 40HX 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 8GB)
Larger VRAM bandwidth (768.0GB/s vs 448.0GB/s)
5888 additional rendering cores
NVIDIA CMP 40HX 's Advantages
Boost Clock1650MHz
Lower TDP (185W vs 450W)
Score
Benchmark
FP32 (float)
Moore Threads MTT S4000
+223%
24.58 TFLOPS
CMP 40HX
7.603 TFLOPS
Graphics Card
Unknown
Release Date
Feb 2021
MUSA-Chunxiao
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 1.0 x4
Clock Speeds
1500 MHz
Base Clock
1470 MHz
-
Boost Clock
1650 MHz
2000 MHz
Memory Clock
1750 MHz
Memory
48GB
Memory Size
8GB
GDDR6
Memory Type
GDDR6
384bit
Memory Bus
256bit
768.0GB/s
Bandwidth
448.0GB/s
Render Config
64
Compute Units
-
-
SM Count
36
8192
Shading Units
2304
512
TMUs
144
512
ROPs
64
128
Tensor Cores
288
-
RT Cores
36
-
L1 Cache
64 KB (per SM)
4 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
768.0 GPixel/s
Pixel Rate
105.6 GPixel/s
768.0 GTexel/s
Texture Rate
237.6 GTexel/s
49.15 TFLOPS
FP16 (half)
15.21 TFLOPS
24.58 TFLOPS
FP32 (float)
7.603 TFLOPS
384.0 GFLOPS
FP64 (double)
237.6 GFLOPS
Board Design
450W
TDP
185W
850 W
Suggested PSU
450 W
4x DisplayPort 1.4a
Outputs
No outputs
2x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
MTT Gen 2
GPU Name
TU106
-
GPU Variant
TU106-100-A1
MUSA-Chunxiao
Architecture
Turing
TSMC
Foundry
TSMC
12 nm
Process Size
12 nm
22 billion
Transistors
10.8 billion
Unknown
Die Size
445 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.4
Vulkan
1.3
-
CUDA
7.5
6.5
Shader Model
6.8
