Performance Rating
The A16 PCIe is a professional graphics card by NVIDIA, launched on April 12th, 2021. Built on the 8 nm process, and based on the GA107 graphics processor, the card supports DirectX 12 Ultimate. The GA107 graphics processor is an average sized chip with a die area of 200 mm² and 8,700 million transistors. Unlike the fully unlocked GeForce RTX 3050 8 GB GA107, which uses the same GPU but has all 2560 shaders enabled, NVIDIA has disabled some shading units on the A16 PCIe to reach the product's target shader count. A16 PCIe combines four graphics processors to increase performance. It features 1280 shading units, 40 texture mapping units, and 32 ROPs, per GPU. Also included are 40 tensor cores which help improve the speed of machine learning applications. The card also has 10 raytracing acceleration cores. NVIDIA has paired 64 GB GDDR6 memory with the A16 PCIe, which are connected using a 128-bit memory interface per GPU (each GPU manages 16,384 MB). The GPU is operating at a frequency of 1312 MHz, which can be boosted up to 1755 MHz, memory is running at 1563 MHz (12.5 Gbps effective).
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering AdditionalMemory
Memory Size
Memory Type
Memory Bandwidth
Memory Bus Width
ML Performance
FP16 (Half Precision)
BF16 (Brain Float)
TF32 (TensorFloat)
Compute Power
FP32 (Single Precision)
FP64 (Double Precision)
CUDA Cores
RT Cores
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
PCIe Version
ML Software Support
CUDA Version
Clocks & Performance
Base Clock
Boost Clock
Memory Clock
Power Consumption
TDP/TGP
Recommended PSU
Power Connector
Rendering
Texture Units (TMU)
ROP
L2 Cache
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
