NVIDIA GeForce RTX 4070 SUPER vs Moore Threads MTT S3000
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 SUPER and 32GB VRAM Moore Threads MTT S3000 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 4070 SUPER 's Advantages
Boost Clock2475MHz
Larger VRAM bandwidth (504.2GB/s vs 448.0GB/s)
3072 additional rendering cores
Lower TDP (220W vs 250W)
Moore Threads MTT S3000 's Advantages
More VRAM (32GB vs 12GB)
Score
Benchmark
FP32 (float)
GeForce RTX 4070 SUPER
+128%
35.48 TFLOPS
Moore Threads MTT S3000
15.56 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
1980 MHz
Base Clock
1900 MHz
2475 MHz
Boost Clock
0 MHz
1313 MHz
Memory Clock
1750 MHz
Memory
12GB
Memory Size
32GB
GDDR6X
Memory Type
GDDR6
192bit
Memory Bus
256bit
504.2GB/s
Bandwidth
448.0GB/s
Render Config
-
Compute Units
32
56
SM Count
-
7168
Shading Units
4096
224
TMUs
256
80
ROPs
256
224
Tensor Cores
-
56
RT Cores
-
128 KB (per SM)
L1 Cache
-
48 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
198.0 GPixel/s
Pixel Rate
486.4 GPixel/s
554.4 GTexel/s
Texture Rate
486.4 GTexel/s
35.48 TFLOPS
FP16 (half)
31.13 TFLOPS
35.48 TFLOPS
FP32 (float)
15.56 TFLOPS
554.4 GFLOPS
FP64 (double)
243.2 GFLOPS
Board Design
220W
TDP
250W
550 W
Suggested PSU
600 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
2x DisplayPort 1.4a
1x 16-pin
Power Connectors
1x 8-pin
Graphics Processor
AD104
GPU Name
MTT Gen 2
AD104-350-A1
GPU Variant
-
Ada Lovelace
Architecture
MUSA-Chunxiao
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
35.8 billion
Transistors
22 billion
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
