Performance Rating
ZOTAC RTX 3090 Trinity outperforms Intel Arc B770 by 72.93% in the overall GPU ARK performance rating
ZOTAC RTX 3090 Trinity
The ZOTAC RTX 3090 Trinity dramatically outperforms the Intel Arc B770, leading by 73% in the overall GPI performance index. For machine learning, the ZOTAC RTX 3090 Trinity has the edge in VRAM (24 vs 16 GB). For gaming, the ZOTAC RTX 3090 Trinity delivers 81% more FP32 throughput, and the ZOTAC RTX 3090 Trinity has 156% more RT cores. In performance per watt, the ZOTAC RTX 3090 Trinity is 16% more efficient at 350W 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
+50%
24
ГБ
Memory Type
Memory Bandwidth
Memory Bus Width
ML Performance
FP16 (Half Precision)
+11%
39.32
TFLOPS
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
+81%
35.58
TFLOPS
FP64 (Double Precision)
+342%
2.458
TFLOPS
CUDA Cores
+156%
10,496
RT Cores
+156%
82
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
82
PCIe Version
ML Software Support
CUDA Version
CUDA Toolkit (first supported)
CUDA Toolkit status
Clocks & Performance
Base Clock
+51%
2,100
Boost Clock
+42%
2,400
Memory Clock
+64%
2,000
Power Consumption
Recommended PSU
-27%
550 W
Power Connector
TDP/TGP
-36%
225 W
Rendering
Texture Units (TMU)
+28%
328
ROP
+156%
82
L2 Cache
6 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
