GeForce RTX 3070 vs Moore Threads MTT S4000
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3070 and 48GB VRAM Moore Threads MTT S4000 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3070 's Advantages
Boost Clock1725MHz
Lower TDP (220W vs 450W)
Moore Threads MTT S4000 's Advantages
More VRAM (48GB vs 8GB)
Larger VRAM bandwidth (768.0GB/s vs 448.0GB/s)
2304 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 3070
20310
Moore Threads MTT S4000
+21%
24580
Graphics Card
Sep 2020
Release Date
Unknown
GeForce 30
Generation
MUSA-Chunxiao
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1500 MHz
Base Clock
1500 MHz
1725 MHz
Boost Clock
-
1750 MHz
Memory Clock
2000 MHz
Memory
8GB
Memory Size
48GB
GDDR6
Memory Type
GDDR6
256bit
Memory Bus
384bit
448.0GB/s
Bandwidth
768.0GB/s
Render Config
-
Compute Units
64
46
SM Count
-
5888
Shading Units
8192
184
TMUs
512
96
ROPs
512
184
Tensor Cores
128
46
RT Cores
-
128 KB (per SM)
L1 Cache
-
4 MB
L2 Cache
4 MB
Theoretical Performance
165.6 GPixel/s
Pixel Rate
768.0 GPixel/s
317.4 GTexel/s
Texture Rate
768.0 GTexel/s
20.31 TFLOPS
FP16 (half)
49.15 TFLOPS
20.31 TFLOPS
FP32 (float)
24.58 TFLOPS
317.4 GFLOPS
FP64 (double)
384.0 GFLOPS
Board Design
220W
TDP
450W
550 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
GA104
GPU Name
MTT Gen 2
GA104-300-A1
GPU Variant
-
Ampere
Architecture
MUSA-Chunxiao
Samsung
Foundry
TSMC
8 nm
Process Size
12 nm
17.4 billion
Transistors
22 billion
392 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
