Performance Rating
NVIDIA H200 SXM 141 GB outperforms GALAX GTX 980 Ti HOF by 1,127.32% in the overall GPU ARK performance rating
NVIDIA H200 SXM 141 GB
Expert Comparison
GALAX GTX 980 Ti HOF от 2015 года с архитектурой Maxwell 2.0 и 6 ГБ GDDR5 памяти хорошо подходит для игр и базовых вычислений. NVIDIA H200 SXM 141 GB с архитектурой Hopper и 141 ГБ HBM3e памяти значительно превосходит её по многим параметрам, особенно по пропускной способности и количеству ядер, что делает её идеальной для вычислительных задач и AI.
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Benchmarks AdditionalMemory
Memory Size
+2,250%
141
ГБ
Memory Type
Memory Bandwidth
4.89 TB/s
Memory Bus Width
ML Performance
FP16 (Half Precision)
267.6
TFLOPS
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
+820%
66.91
TFLOPS
FP64 (Double Precision)
+14,623%
33.45
TFLOPS
CUDA Cores
+500%
16,896
RT Cores
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
132
PCIe Version
ML Software Support
CUDA Version
9.0
CUDA Toolkit (first supported)
CUDA Toolkit (deprecated)
CUDA Toolkit (support removed)
CUDA Toolkit status
Clocks & Performance
Base Clock
+26%
1,500
Boost Clock
+53%
1,980
Memory Clock
1,593
Power Consumption
Recommended PSU
-45%
600 W
Power Connector
TDP/TGP
-64%
250 W
Rendering
Texture Units (TMU)
+200%
528
ROP
L2 Cache
+1,567%
50 MB
Benchmarks
MLPerf, llama2-70b-99.9 (UNSET)
MLPerf, llama2-70b-99.9 (fp16)
MLPerf, llama2-70b-99.9 (fp8)
MLPerf, llama3.1-405b (fp16)
MLPerf, llama3.1-405b (fp8)
MLPerf, llama3.1-8b (fp8)
MLPerf, deepseek-r1 (fp8)
MLPerf, mixtral-8x7b (fp8)
Additional
Slots
SXM Module
Release Date
Display Outputs
Rent on Intelion Cloud
Available for rent on Intelion Cloud
