NVIDIA GeForce RTX 4070 GDDR6 vs Moore Threads MTT S50
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 GDDR6 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 4070 GDDR6 's Advantages
Released 10 months late
Boost Clock2475MHz
More VRAM (12GB vs 8GB)
Larger VRAM bandwidth (480.0GB/s vs 448.0GB/s)
3840 additional rendering cores
Moore Threads MTT S50 's Advantages
Lower TDP (85W vs 200W)
Score
Benchmark
FP32 (float)
GeForce RTX 4070 GDDR6
+493%
29.15 TFLOPS
MTT S50
4.915 TFLOPS
Graphics Card
Aug 2024
Release Date
Oct 2023
GeForce 40
Generation
MUSA-Chunxiao
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1920 MHz
Base Clock
1200 MHz
2475 MHz
Boost Clock
0 MHz
2500 MHz
Memory Clock
1750 MHz
Memory
12GB
Memory Size
8GB
GDDR6
Memory Type
GDDR6
192bit
Memory Bus
256bit
480.0GB/s
Bandwidth
448.0GB/s
Render Config
-
Compute Units
16
46
SM Count
5888
Shading Units
2048
184
TMUs
128
64
ROPs
128
184
Tensor Cores
46
RT Cores
128 KB (per SM)
L1 Cache
36 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
158.4 GPixel/s
Pixel Rate
153.6 GPixel/s
455.4 GTexel/s
Texture Rate
153.6 GTexel/s
29.15 TFLOPS
FP16 (half)
9.830 TFLOPS
29.15 TFLOPS
FP32 (float)
4.915 TFLOPS
455.4 GFLOPS
FP64 (double)
76.80 GFLOPS
Board Design
200W
TDP
85W
550 W
Suggested PSU
250 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.0
2x DisplayPort 1.2
1x 16-pin
Power Connectors
1x 6-pin
Graphics Processor
AD104
GPU Name
MTT Gen 1
AD104-2XX-A1
GPU Variant
Ada Lovelace
Architecture
MUSA-Chunxiao
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
35.8 billion
Transistors
Unknown
294 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
6.8
Shader Model
6.5
