Performance Rating
NVIDIA RTX PRO 4000 Blackwell SFF outperforms ZOTAC RTX 2070 Plus by 124.16% in the overall GPU ARK performance rating
ZOTAC RTX 2070 Plus
The NVIDIA RTX PRO 4000 Blackwell SFF dramatically outperforms the ZOTAC RTX 2070 Plus, leading by 124% in the overall GPI performance index. For machine learning, the NVIDIA RTX PRO 4000 Blackwell SFF has the edge in VRAM (24 vs 8 GB) and FP16 performance (+72%). For gaming, the NVIDIA RTX PRO 4000 Blackwell SFF delivers 244% more FP32 throughput, and the NVIDIA RTX PRO 4000 Blackwell SFF has 94% more RT cores. In performance per watt, the NVIDIA RTX PRO 4000 Blackwell SFF is 759% more efficient at 70W TDP vs 175W for the ZOTAC RTX 2070 Plus.
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering AdditionalMemory
Memory Size
+200%
24
ГБ
Memory Type
Memory Bandwidth
Memory Bus Width
ML Performance
FP16 (Half Precision)
+72%
25.66
TFLOPS
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
+244%
25.66
TFLOPS
FP64 (Double Precision)
+72%
0.401
TFLOPS
CUDA Cores
+289%
8,960
RT Cores
+94%
70
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
+94%
70
PCIe Version
ML Software Support
CUDA Version
12.0
CUDA Toolkit (first supported)
CUDA Toolkit status
Clocks & Performance
Base Clock
577
Boost Clock
1,432
Memory Clock
1,125
Power Consumption
Recommended PSU
-44%
250 W
Power Connector
TDP/TGP
-60%
70 W
Rendering
Texture Units (TMU)
+94%
280
ROP
+94%
70
L2 Cache
+1,100%
48 MB
Additional
Slots
Release Date
Display Outputs
Renting is cheaper than buying
H100 80Gb SXM (80GB)
NVIDIA
Флагманская GPU на архитектуре Hopper с 80 ГБ памяти HBM3 в форм-факторе SXM. Создана для обучения и инференса больших языковых моделей, HPC задач. Поддерживает FP64, FP32, TF32, FP16, BF16, FP8 и INT8 вычисления с Tensor Cores 4-го поколения.
from 299.11 RUB/hour
