NVIDIA GeForce RTX 4070 Ti SUPER vs Moore Threads MTT S4000
We compared two Desktop platform GPUs: 16GB VRAM GeForce RTX 4070 Ti SUPER 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 4070 Ti SUPER 's Advantages
Boost Clock2610MHz
256 additional rendering cores
Lower TDP (285W vs 450W)
Moore Threads MTT S4000 's Advantages
More VRAM (48GB vs 16GB)
Larger VRAM bandwidth (768.0GB/s vs 672.3GB/s)
Score
Benchmark
FP32 (float)
GeForce RTX 4070 Ti SUPER
+79%
44.1 TFLOPS
Moore Threads MTT S4000
24.58 TFLOPS
Graphics Card
Jan 2024
Release Date
Unknown
GeForce 40
Generation
MUSA-Chunxiao
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
2340 MHz
Base Clock
1500 MHz
2610 MHz
Boost Clock
-
1313 MHz
Memory Clock
2000 MHz
Memory
16GB
Memory Size
48GB
GDDR6X
Memory Type
GDDR6
256bit
Memory Bus
384bit
672.3GB/s
Bandwidth
768.0GB/s
Render Config
-
Compute Units
64
66
SM Count
-
8448
Shading Units
8192
264
TMUs
512
96
ROPs
512
264
Tensor Cores
128
66
RT Cores
-
128 KB (per SM)
L1 Cache
-
48 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
250.6 GPixel/s
Pixel Rate
768.0 GPixel/s
689.0 GTexel/s
Texture Rate
768.0 GTexel/s
44.10 TFLOPS
FP16 (half)
49.15 TFLOPS
44.10 TFLOPS
FP32 (float)
24.58 TFLOPS
689.0 GFLOPS
FP64 (double)
384.0 GFLOPS
Board Design
285W
TDP
450W
600 W
Suggested PSU
850 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
4x DisplayPort 1.4a
1x 16-pin
Power Connectors
2x 8-pin
Graphics Processor
AD103
GPU Name
MTT Gen 2
AD103-275-A1
GPU Variant
-
Ada Lovelace
Architecture
MUSA-Chunxiao
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
45.9 billion
Transistors
22 billion
379 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
8.9
CUDA
-
6.7
Shader Model
6.5
