NVIDIA GeForce RTX 3070 Ti GA102 vs Moore Threads MTT S4000
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3070 Ti GA102 and 48GB VRAM Moore Threads MTT S4000 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 3070 Ti GA102 's Advantages
Boost Clock1770MHz
Lower TDP (290W vs 450W)
Moore Threads MTT S4000 's Advantages
More VRAM (48GB vs 8GB)
Larger VRAM bandwidth (768.0GB/s vs 608.3GB/s)
2048 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 3070 Ti GA102
21.75 TFLOPS
Moore Threads MTT S4000
+13%
24.58 TFLOPS
Graphics Card
Oct 2022
Release Date
Unknown
GeForce 30
Generation
MUSA-Chunxiao
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1575 MHz
Base Clock
1500 MHz
1770 MHz
Boost Clock
-
1188 MHz
Memory Clock
2000 MHz
Memory
8GB
Memory Size
48GB
GDDR6X
Memory Type
GDDR6
256bit
Memory Bus
384bit
608.3GB/s
Bandwidth
768.0GB/s
Render Config
-
Compute Units
64
48
SM Count
-
6144
Shading Units
8192
192
TMUs
512
96
ROPs
512
192
Tensor Cores
128
48
RT Cores
-
128 KB (per SM)
L1 Cache
-
4 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
169.9 GPixel/s
Pixel Rate
768.0 GPixel/s
339.8 GTexel/s
Texture Rate
768.0 GTexel/s
21.75 TFLOPS
FP16 (half)
49.15 TFLOPS
21.75 TFLOPS
FP32 (float)
24.58 TFLOPS
339.8 GFLOPS
FP64 (double)
384.0 GFLOPS
Board Design
290W
TDP
450W
600 W
Suggested PSU
850 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
4x DisplayPort 1.4a
1x 12-pin
Power Connectors
2x 8-pin
Graphics Processor
GA102
GPU Name
MTT Gen 2
GA102-150-A1
GPU Variant
-
Ampere
Architecture
MUSA-Chunxiao
Samsung
Foundry
TSMC
8 nm
Process Size
12 nm
28.3 billion
Transistors
22 billion
628 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
8.6
CUDA
-
6.6
Shader Model
6.5
