NVIDIA B100 vs Moore Threads MTT S70
We compared two Desktop platform GPUs: 96GB VRAM B100 and 7GB VRAM MTT S70 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA B100 's Advantages
Released 1 years and 1 months late
Boost Clock1837MHz
More VRAM (96GB vs 7GB)
Larger VRAM bandwidth (4.10TB/s vs 392.0GB/s)
13312 additional rendering cores
Moore Threads MTT S70 's Advantages
Lower TDP (220W vs 1000W)
Score
Benchmark
FP32 (float)
B100
+441%
62.08 TFLOPS
MTT S70
11.47 TFLOPS
Graphics Card
Nov 2024
Release Date
Oct 2023
Server Blackwell
Generation
MUSA-Chunxiao
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1665 MHz
Base Clock
1600 MHz
1837 MHz
Boost Clock
0 MHz
2000 MHz
Memory Clock
1750 MHz
Memory
96GB
Memory Size
7GB
HBM3e
Memory Type
GDDR6
4096bit
Memory Bus
224bit
4.10TB/s
Bandwidth
392.0GB/s
Render Config
-
Compute Units
28
132
SM Count
16896
Shading Units
3584
528
TMUs
224
24
ROPs
224
528
Tensor Cores
-
RT Cores
256 KB (per SM)
L1 Cache
50 MB
L2 Cache
0 MB
-
-
-
Theoretical Performance
44.09 GPixel/s
Pixel Rate
358.4 GPixel/s
969.9 GTexel/s
Texture Rate
358.4 GTexel/s
248.3 TFLOPS
FP16 (half)
22.94 TFLOPS
62.08 TFLOPS
FP32 (float)
11.47 TFLOPS
31.04 TFLOPS
FP64 (double)
179.2 GFLOPS
Board Design
1000W
TDP
220W
1400 W
Suggested PSU
550 W
No outputs
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
-
Power Connectors
1x 8-pin
Graphics Processor
GB102
GPU Name
MTT Gen 2
-
GPU Variant
Blackwell
Architecture
MUSA-Chunxiao
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
104 billion
Transistors
22 billion
Unknown
Die Size
Unknown
Graphics Features
N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.4
10.1
CUDA
N/A
Shader Model
6.5
