Moore Threads MTT S2000 vs NVIDIA B100
We compared two Desktop platform GPUs: 32GB VRAM Moore Threads MTT S2000 and 96GB VRAM B100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Moore Threads MTT S2000 's Advantages
Lower TDP (150W vs 1000W)
NVIDIA B100 's Advantages
Boost Clock1837MHz
More VRAM (96GB vs 32GB)
Larger VRAM bandwidth (4.10TB/s vs 448.0GB/s)
12800 additional rendering cores
Score
Benchmark
FP32 (float)
Moore Threads MTT S2000
10.65 TFLOPS
B100
+482%
62.08 TFLOPS
Graphics Card
Unknown
Release Date
Nov 2024
MUSA-Chunxiao
Generation
Server Blackwell
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1300 MHz
Base Clock
1665 MHz
-
Boost Clock
1837 MHz
1750 MHz
Memory Clock
2000 MHz
Memory
32GB
Memory Size
96GB
GDDR6
Memory Type
HBM3e
256bit
Memory Bus
4096bit
448.0GB/s
Bandwidth
4.10TB/s
Render Config
32
Compute Units
-
-
SM Count
132
4096
Shading Units
16896
256
TMUs
528
256
ROPs
24
-
Tensor Cores
528
-
-
-
-
L1 Cache
256 KB (per SM)
4 MB
L2 Cache
50 MB
-
-
-
Theoretical Performance
332.8 GPixel/s
Pixel Rate
44.09 GPixel/s
332.8 GTexel/s
Texture Rate
969.9 GTexel/s
21.30 TFLOPS
FP16 (half)
248.3 TFLOPS
10.65 TFLOPS
FP32 (float)
62.08 TFLOPS
166.4 GFLOPS
FP64 (double)
31.04 TFLOPS
Board Design
150W
TDP
1000W
450 W
Suggested PSU
1400 W
2x DisplayPort 1.2
Outputs
No outputs
1x 8-pin
Power Connectors
-
Graphics Processor
MTT Gen 1
GPU Name
GB102
-
-
-
MUSA-Chunxiao
Architecture
Blackwell
TSMC
Foundry
TSMC
12 nm
Process Size
5 nm
Unknown
Transistors
104 billion
Unknown
Die Size
Unknown
Graphics Features
12 Ultimate (12_2)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.4
Vulkan
N/A
-
CUDA
10.1
6.5
Shader Model
N/A
