NVIDIA GeForce RTX 5070 Ti vs Moore Threads MTT S50
We compared two Desktop platform GPUs: 16GB VRAM GeForce RTX 5070 Ti and 8GB VRAM MTT S50 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 5070 Ti 's Advantages
Released 1 years and 4 months late
Boost Clock2452MHz
More VRAM (16GB vs 8GB)
Larger VRAM bandwidth (896.0GB/s vs 448.0GB/s)
6912 additional rendering cores
Moore Threads MTT S50 's Advantages
Lower TDP (85W vs 300W)
Score
Benchmark
FP32 (float)
GeForce RTX 5070 Ti
+793%
43.94 TFLOPS
MTT S50
4.915 TFLOPS
Graphics Card
Feb 2025
Release Date
Oct 2023
GeForce 50
Generation
MUSA-Chunxiao
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
2295 MHz
Base Clock
1200 MHz
2452 MHz
Boost Clock
0 MHz
1750 MHz
Memory Clock
1750 MHz
Memory
16GB
Memory Size
8GB
GDDR7
Memory Type
GDDR6
256bit
Memory Bus
256bit
896.0GB/s
Bandwidth
448.0GB/s
Render Config
-
Compute Units
16
70
SM Count
8960
Shading Units
2048
280
TMUs
128
96
ROPs
128
280
Tensor Cores
70
RT Cores
128 KB (per SM)
L1 Cache
48 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
235.4 GPixel/s
Pixel Rate
153.6 GPixel/s
686.6 GTexel/s
Texture Rate
153.6 GTexel/s
43.94 TFLOPS
FP16 (half)
9.830 TFLOPS
43.94 TFLOPS
FP32 (float)
4.915 TFLOPS
686.6 GFLOPS
FP64 (double)
76.80 GFLOPS
Board Design
300W
TDP
85W
700 W
Suggested PSU
250 W
1x HDMI 2.1b
3x DisplayPort 2.1b
Outputs
1x HDMI 2.0
2x DisplayPort 1.2
1x 16-pin
Power Connectors
1x 6-pin
Graphics Processor
GB203
GPU Name
MTT Gen 1
GB203-300-A1
GPU Variant
Blackwell 2.0
Architecture
MUSA-Chunxiao
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
45.6 billion
Transistors
Unknown
378 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
1.4
Vulkan
1.4
12.0
CUDA
6.8
Shader Model
6.5
