NVIDIA H200 SXM 141 GB vs Moore Threads MTT S80
We compared two Desktop platform GPUs: 141GB VRAM H200 SXM 141 GB and 16GB VRAM MTT S80 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA H200 SXM 141 GB 's Advantages
Released 1 years and 1 months late
Boost Clock1980MHz
More VRAM (141GB vs 16GB)
Larger VRAM bandwidth (4.89TB/s vs 448.0GB/s)
12800 additional rendering cores
Moore Threads MTT S80 's Advantages
Lower TDP (255W vs 700W)
Score
Benchmark
FP32 (float)
H200 SXM 141 GB
+353%
66.91 TFLOPS
MTT S80
14.75 TFLOPS
Graphics Card
Nov 2024
Release Date
Oct 2023
Server Hopper
Generation
MUSA-Chunxiao
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1500 MHz
Base Clock
1800 MHz
1980 MHz
Boost Clock
0 MHz
1593 MHz
Memory Clock
1750 MHz
Memory
141GB
Memory Size
16GB
HBM3e
Memory Type
GDDR6
6144bit
Memory Bus
256bit
4.89TB/s
Bandwidth
448.0GB/s
Render Config
-
Compute Units
32
132
SM Count
16896
Shading Units
4096
528
TMUs
256
24
ROPs
256
528
Tensor Cores
-
RT Cores
256 KB (per SM)
L1 Cache
50 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
47.52 GPixel/s
Pixel Rate
460.8 GPixel/s
1045 GTexel/s
Texture Rate
460.8 GTexel/s
267.6 TFLOPS
FP16 (half)
29.49 TFLOPS
66.91 TFLOPS
FP32 (float)
14.75 TFLOPS
33.45 TFLOPS
FP64 (double)
230.4 GFLOPS
Board Design
700W
TDP
255W
1100 W
Suggested PSU
600 W
No outputs
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
8-pin EPS
Power Connectors
1x 8-pin
Graphics Processor
GH100
GPU Name
MTT Gen 2
-
GPU Variant
Hopper
Architecture
MUSA-Chunxiao
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
80 billion
Transistors
22 billion
814 mm²
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
9.0
CUDA
N/A
Shader Model
6.5
