NVIDIA CMP 40HX vs Moore Threads MTT S10
We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 2GB VRAM MTT S10 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 40HX 's Advantages
Boost Clock1650MHz
More VRAM (8GB vs 2GB)
Larger VRAM bandwidth (448.0GB/s vs 112.0GB/s)
1280 additional rendering cores
Moore Threads MTT S10 's Advantages
Released 2 years and 8 months late
Lower TDP (30W vs 185W)
Score
Benchmark
FP32 (float)
CMP 40HX
+271%
7.603 TFLOPS
MTT S10
2.048 TFLOPS
Graphics Card
Feb 2021
Release Date
Oct 2023
Mining GPUs
Generation
MUSA-Chunxiao
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 4.0 x8
Clock Speeds
1470 MHz
Base Clock
1000 MHz
1650 MHz
Boost Clock
0 MHz
1750 MHz
Memory Clock
1750 MHz
Memory
8GB
Memory Size
2GB
GDDR6
Memory Type
GDDR6
256bit
Memory Bus
64bit
448.0GB/s
Bandwidth
112.0GB/s
Render Config
-
Compute Units
8
36
SM Count
2304
Shading Units
1024
144
TMUs
64
64
ROPs
64
288
Tensor Cores
36
RT Cores
64 KB (per SM)
L1 Cache
4 MB
L2 Cache
1024 KB
-
-
-
Theoretical Performance
105.6 GPixel/s
Pixel Rate
64.00 GPixel/s
237.6 GTexel/s
Texture Rate
64.00 GTexel/s
15.21 TFLOPS
FP16 (half)
4.096 TFLOPS
7.603 TFLOPS
FP32 (float)
2.048 TFLOPS
237.6 GFLOPS
FP64 (double)
32.00 GFLOPS
Board Design
185W
TDP
30W
450 W
Suggested PSU
200 W
No outputs
Outputs
2x DisplayPort 1.2
1x 8-pin
Power Connectors
None
Graphics Processor
TU106
GPU Name
MTT Gen 1
TU106-100-A1
GPU Variant
Turing
Architecture
MUSA-Chunxiao
TSMC
Foundry
TSMC
12 nm
Process Size
12 nm
10.8 billion
Transistors
Unknown
445 mm²
Die Size
Unknown
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.4
7.5
CUDA
6.8
Shader Model
6.5
