Moore Threads MTT S1000M vs NVIDIA L20
We compared two Desktop platform GPUs: 4GB VRAM Moore Threads MTT S1000M and 48GB VRAM L20 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Moore Threads MTT S1000M 's Advantages
Lower TDP (35W vs 275W)
NVIDIA L20 's Advantages
Released 1 years and 4 months late
Boost Clock2520MHz
More VRAM (48GB vs 4GB)
Larger VRAM bandwidth (864.0GB/s vs 224.0GB/s)
10752 additional rendering cores
Score
Benchmark
FP32 (float)
Moore Threads MTT S1000M
2.048 TFLOPS
L20
+2797%
59.35 TFLOPS
Graphics Card
Jul 2022
Release Date
Nov 2023
MUSA-Chunxiao
Generation
Tesla Ada
Desktop
Type
Desktop
PCIe 4.0 x8
Bus Interface
PCIe 4.0 x16
Clock Speeds
1000 MHz
Base Clock
1440 MHz
-
Boost Clock
2520 MHz
1750 MHz
Memory Clock
2250 MHz
Memory
4GB
Memory Size
48GB
GDDR6
Memory Type
GDDR6
128bit
Memory Bus
384bit
224.0GB/s
Bandwidth
864.0GB/s
Render Config
8
Compute Units
-
-
SM Count
92
1024
Shading Units
11776
64
TMUs
368
64
ROPs
128
-
Tensor Cores
368
-
RT Cores
92
-
L1 Cache
128 KB (per SM)
1024 KB
L2 Cache
96 MB
-
-
-
Theoretical Performance
64.00 GPixel/s
Pixel Rate
322.6 GPixel/s
64.00 GTexel/s
Texture Rate
927.4 GTexel/s
4.096 TFLOPS
FP16 (half)
59.35 TFLOPS
2.048 TFLOPS
FP32 (float)
59.35 TFLOPS
32.00 GFLOPS
FP64 (double)
927.4 GFLOPS
Board Design
35W
TDP
275W
200 W
Suggested PSU
600 W
2x DisplayPort 1.2
Outputs
4x DisplayPort 1.4a
None
Power Connectors
1x 16-pin
Graphics Processor
MTT Gen 1
GPU Name
AD102
-
GPU Variant
AD102
MUSA-Chunxiao
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
12 nm
Process Size
5 nm
Unknown
Transistors
76.3 billion
Unknown
Die Size
609 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.4
Vulkan
1.3
-
CUDA
8.9
6.5
Shader Model
6.7
