Performance Rating
NVIDIA RTX PRO 4000 Blackwell SFF
For ML workloads, the NVIDIA RTX PRO 4000 Blackwell SFF is far more suitable with its tensor cores and FP16 support, while the AMD Radeon HD 7560G IGP targets different use cases. For gaming, the NVIDIA RTX PRO 4000 Blackwell SFF delivers 6495% more FP32 throughput, and the NVIDIA RTX PRO 4000 Blackwell SFF supports hardware ray tracing. In performance per watt, the NVIDIA RTX PRO 4000 Blackwell SFF is 3197% more efficient at 70W TDP vs 35W for the AMD Radeon HD 7560G IGP.
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering AdditionalMemory
Memory Size
24
ГБ
Memory Type
Memory Bandwidth
Memory Bus Width
ML Performance
FP16 (Half Precision)
25.66
TFLOPS
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
+6,495%
25.66
TFLOPS
FP64 (Double Precision)
0.401
TFLOPS
CUDA Cores
+3,400%
8,960
RT Cores
70
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
70
PCIe Version
ML Software Support
CUDA Version
CUDA Toolkit (first supported)
CUDA Toolkit status
Clocks & Performance
Base Clock
+16%
577
Boost Clock
+88%
1,432
Memory Clock
1,125
Power Consumption
Recommended PSU
Power Connector
TDP/TGP
-50%
35 W
Rendering
Texture Units (TMU)
+1,650%
280
ROP
70
L2 Cache
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
