Performance Rating
NVIDIA B300 outperforms Palit RTX 4080 SUPER GamingPro OC by 235.96% in the overall GPU ARK performance rating
Palit RTX 4080 SUPER GamingPro OC
The NVIDIA B300 dramatically outperforms the Palit RTX 4080 SUPER GamingPro OC, leading by 236% in the overall GPI performance index. For machine learning, the Palit RTX 4080 SUPER GamingPro OC has the edge in FP16 performance (+4239%). For gaming, the NVIDIA B300 delivers 44% more FP32 throughput, and the Palit RTX 4080 SUPER GamingPro OC supports hardware ray tracing. In performance per watt, the Palit RTX 4080 SUPER GamingPro OC is 204% more efficient at 320W TDP vs 1400W for the NVIDIA B300.
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering AdditionalMemory
Memory Size
+800%
144
ГБ ×2 (288 ГБ)
Memory Type
Memory Bandwidth
4.10 TB/s
×2 (8.2 TB/s)
Memory Bus Width
ML Performance
FP16 (Half Precision)
+4,239%
53.45
TFLOPS
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
+44%
76.99
TFLOPS
FP64 (Double Precision)
+44%
1.2029
TFLOPS
CUDA Cores
+85%
18,944
×2 (37888)
RT Cores
80
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
+85%
148
PCIe Version
ML Software Support
CUDA Version
10.3
CUDA Toolkit (first supported)
CUDA Toolkit status
Clocks & Performance
Base Clock
+38%
2,295
Boost Clock
+28%
2,610
Memory Clock
+39%
2,000
Power Consumption
Recommended PSU
-61%
700 W
Power Connector
TDP/TGP
-77%
320 W
Rendering
Texture Units (TMU)
+85%
592
×2 (1184)
ROP
80
L2 Cache
+28%
64 MB
Additional
Slots
SXM Module
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
