NVIDIA GeForce GTX 650 Ti vs Moore Threads MTT S4000
We compared two Desktop platform GPUs: 1024MB VRAM GeForce GTX 650 Ti 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 GTX 650 Ti 's Advantages
Lower TDP (110W vs 450W)
Moore Threads MTT S4000 's Advantages
More VRAM (48GB vs 1024GB)
Larger VRAM bandwidth (768.0GB/s vs 86.40GB/s)
7424 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce GTX 650 Ti
1.425 TFLOPS
Moore Threads MTT S4000
+1624%
24.58 TFLOPS
Graphics Card
Oct 2012
Release Date
Unknown
GeForce 600
Generation
MUSA-Chunxiao
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
-
Base Clock
1500 MHz
-
-
-
1350 MHz
Memory Clock
2000 MHz
Memory
1024MB
Memory Size
48GB
GDDR5
Memory Type
GDDR6
128bit
Memory Bus
384bit
86.40GB/s
Bandwidth
768.0GB/s
Render Config
-
Compute Units
64
-
-
-
768
Shading Units
8192
64
TMUs
512
16
ROPs
512
-
Tensor Cores
128
-
-
-
16 KB (per SMX)
L1 Cache
-
256 KB
L2 Cache
4 MB
-
-
-
Theoretical Performance
14.85 GPixel/s
Pixel Rate
768.0 GPixel/s
59.39 GTexel/s
Texture Rate
768.0 GTexel/s
-
FP16 (half)
49.15 TFLOPS
1425 GFLOPS
FP32 (float)
24.58 TFLOPS
59.39 GFLOPS
FP64 (double)
384.0 GFLOPS
Board Design
110W
TDP
450W
300 W
Suggested PSU
850 W
2x DVI
1x mini-HDMI 1.4a
Outputs
4x DisplayPort 1.4a
1x 6-pin
Power Connectors
2x 8-pin
Graphics Processor
GK106
GPU Name
MTT Gen 2
GK106-220-A1
GPU Variant
-
Kepler
Architecture
MUSA-Chunxiao
TSMC
Foundry
TSMC
28 nm
Process Size
12 nm
2.54 billion
Transistors
22 billion
221 mm²
Die Size
Unknown
Graphics Features
12 (11_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.4
3.0
CUDA
-
5.1
Shader Model
6.5
