Performance Rating
Intel Arc B770 outperforms NVIDIA RTX PRO 3000 Blackwell Mobile by 4.08% in the overall GPU ARK performance rating
NVIDIA RTX PRO 3000 Blackwell Mobile
The Intel Arc B770 marginally outperforms the NVIDIA RTX PRO 3000 Blackwell Mobile, leading by 4% in the overall GPI performance index. For machine learning, the Intel Arc B770 has the edge in FP16 performance (+108%) and VRAM (16 vs 12 GB). For gaming, the NVIDIA RTX PRO 3000 Blackwell Mobile has 44% more RT cores. In performance per watt, the NVIDIA RTX PRO 3000 Blackwell Mobile is 261% more efficient at 60W TDP vs 225W for the Intel Arc B770.
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering AdditionalMemory
Memory Size
+33%
16
ГБ
Memory Type
Memory Bandwidth
Memory Bus Width
ML Performance
FP16 (Half Precision)
+108%
39.32
TFLOPS
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
+4%
19.66
TFLOPS
FP64 (Double Precision)
+732%
2.458
TFLOPS
CUDA Cores
4,096
RT Cores
32
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
PCIe Version
ML Software Support
CUDA Version
CUDA Toolkit (first supported)
CUDA Toolkit status
Clocks & Performance
Base Clock
+148%
2,100
Boost Clock
+50%
2,400
Memory Clock
+14%
2,000
Power Consumption
Recommended PSU
Power Connector
TDP/TGP
-73%
60 W
Rendering
Texture Units (TMU)
+39%
256
ROP
32
L2 Cache
16 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
