Moore Threads MTT S50 vs NVIDIA RTX 3500 Embedded Ada Generation
We compared two Desktop platform GPUs: 8GB VRAM MTT S50 and 12GB VRAM RTX 3500 Embedded Ada Generation to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Moore Threads MTT S50 's Advantages
Released 7 months late
Larger VRAM bandwidth (448.0GB/s vs 432.0GB/s)
Lower TDP (85W vs 100W)
NVIDIA RTX 3500 Embedded Ada Generation 's Advantages
Boost Clock2250MHz
More VRAM (12GB vs 8GB)
3072 additional rendering cores
Score
Benchmark
FP32 (float)
MTT S50
4.915 TFLOPS
RTX 3500 Embedded Ada Generation
+368%
23.04 TFLOPS
Graphics Card
Oct 2023
Release Date
Mar 2023
MUSA-Chunxiao
Generation
Quadro Ada-M
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1200 MHz
Base Clock
1725 MHz
0 MHz
Boost Clock
2250 MHz
1750 MHz
Memory Clock
2250 MHz
Memory
8GB
Memory Size
12GB
GDDR6
Memory Type
GDDR6
256bit
Memory Bus
192bit
448.0GB/s
Bandwidth
432.0GB/s
Render Config
16
Compute Units
-
SM Count
40
2048
Shading Units
5120
128
TMUs
160
128
ROPs
64
Tensor Cores
160
RT Cores
40
L1 Cache
128 KB (per SM)
2 MB
L2 Cache
48 MB
-
-
-
Theoretical Performance
153.6 GPixel/s
Pixel Rate
144.0 GPixel/s
153.6 GTexel/s
Texture Rate
360.0 GTexel/s
9.830 TFLOPS
FP16 (half)
23.04 TFLOPS
4.915 TFLOPS
FP32 (float)
23.04 TFLOPS
76.80 GFLOPS
FP64 (double)
360.0 GFLOPS
Board Design
85W
TDP
100W
250 W
Suggested PSU
300 W
1x HDMI 2.0
2x DisplayPort 1.2
Outputs
No outputs
1x 6-pin
Power Connectors
None
Graphics Processor
MTT Gen 1
GPU Name
AD104
GPU Variant
-
MUSA-Chunxiao
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
12 nm
Process Size
5 nm
Unknown
Transistors
35.8 billion
Unknown
Die Size
294 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
8.9
6.5
Shader Model
6.7
