Performance Rating
NVIDIA H200 SXM 141 GB outperforms NVIDIA RTX PRO 4000 Blackwell Embedded by 348.3% in the overall GPU ARK performance rating
NVIDIA RTX PRO 4000 Blackwell Embedded
The NVIDIA H200 SXM 141 GB dramatically outperforms the NVIDIA RTX PRO 4000 Blackwell Embedded, leading by 348% in the overall GPI performance index. For machine learning, the NVIDIA H200 SXM 141 GB has the edge in FP16 performance (+924%) and VRAM (141 vs 16 GB). In performance per watt, the NVIDIA RTX PRO 4000 Blackwell Embedded is 242% more efficient at 80W TDP vs 700W for the NVIDIA H200 SXM 141 GB.
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Benchmarks AdditionalMemory
Memory Size
+781%
141
ГБ
Memory Type
Memory Bandwidth
4.89 TB/s
Memory Bus Width
ML Performance
FP16 (Half Precision)
+924%
267.6
TFLOPS
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
+156%
66.91
TFLOPS
FP64 (Double Precision)
+8,088%
33.45
TFLOPS
CUDA Cores
+120%
16,896
RT Cores
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
+120%
132
PCIe Version
ML Software Support
CUDA Version
12.0
CUDA Toolkit (first supported)
CUDA Toolkit status
Clocks & Performance
Base Clock
+54%
1,500
Boost Clock
+16%
1,980
Memory Clock
1,593
Power Consumption
Recommended PSU
Power Connector
TDP/TGP
-89%
80 W
Rendering
Texture Units (TMU)
+120%
528
ROP
L2 Cache
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
