Moore Threads MTT S3000 vs NVIDIA PG506 242
We compared two Desktop platform GPUs: 32GB VRAM Moore Threads MTT S3000 and 24GB VRAM PG506 242 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Moore Threads MTT S3000 's Advantages
More VRAM (32GB vs 24GB)
512 additional rendering cores
NVIDIA PG506 242 's Advantages
Boost Clock1440MHz
Larger VRAM bandwidth (933.1GB/s vs 448.0GB/s)
Lower TDP (165W vs 250W)
Score
Benchmark
FP32 (float)
Moore Threads MTT S3000
+50%
15.56 TFLOPS
PG506 242
10.32 TFLOPS
Graphics Card
Unknown
Release Date
Apr 2021
MUSA-Chunxiao
Generation
Tesla
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1900 MHz
Base Clock
930 MHz
0 MHz
Boost Clock
1440 MHz
1750 MHz
Memory Clock
1215 MHz
Memory
32GB
Memory Size
24GB
GDDR6
Memory Type
HBM2
256bit
Memory Bus
3072bit
448.0GB/s
Bandwidth
933.1GB/s
Render Config
32
Compute Units
-
-
SM Count
56
4096
Shading Units
3584
256
TMUs
224
256
ROPs
96
-
Tensor Cores
224
-
-
-
-
L1 Cache
192 KB (per SM)
4 MB
L2 Cache
24 MB
-
-
-
Theoretical Performance
486.4 GPixel/s
Pixel Rate
138.2 GPixel/s
486.4 GTexel/s
Texture Rate
322.6 GTexel/s
31.13 TFLOPS
FP16 (half)
10.32 TFLOPS
15.56 TFLOPS
FP32 (float)
10.32 TFLOPS
243.2 GFLOPS
FP64 (double)
5.161 TFLOPS
Board Design
250W
TDP
165W
600 W
Suggested PSU
450 W
2x DisplayPort 1.4a
Outputs
No outputs
1x 8-pin
Power Connectors
8-pin EPS
Graphics Processor
MTT Gen 2
GPU Name
GA100
-
-
-
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
