Performance Rating
NVIDIA B300 outperforms MAXSUN GTX 1050 Terminator M.4 by 4,452.53% in the overall GPU ARK performance rating
NVIDIA B300
The NVIDIA B300 dramatically outperforms the MAXSUN GTX 1050 Terminator M.4, leading by 4453% in the overall GPI performance index. For machine learning, the NVIDIA B300 has the edge in VRAM (144 vs 2 GB) and FP16 performance (+4133%). For gaming, the NVIDIA B300 delivers 4035% more FP32 throughput. In performance per watt, the NVIDIA B300 is 122% more efficient at 1400W TDP vs 75W for the MAXSUN GTX 1050 Terminator M.4.
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering AdditionalMemory
Memory Size
+7,100%
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)
+4,133%
1.2318
TFLOPS
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
+4,035%
76.99
TFLOPS
FP64 (Double Precision)
+1,967%
1.2029
TFLOPS
CUDA Cores
+2,860%
18,944
×2 (37888)
RT Cores
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
+2,860%
148
PCIe Version
ML Software Support
CUDA Version
10.3
CUDA Toolkit (first supported)
CUDA Toolkit (deprecated)
CUDA Toolkit (support removed)
CUDA Toolkit status
Clocks & Performance
Base Clock
+23%
1,665
Boost Clock
+40%
2,032
Memory Clock
+14%
2,000
Power Consumption
Recommended PSU
-86%
250 W
Power Connector
TDP/TGP
-95%
75 W
Rendering
Texture Units (TMU)
+1,380%
592
×2 (1184)
ROP
L2 Cache
50 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
