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