Performance Rating
The RTX PRO 6000 Blackwell Max-Q is an enthusiast-class professional graphics card by NVIDIA, launched on March 18th, 2025. Built on the 5 nm process, and based on the GB202 graphics processor, the card supports DirectX 12 Ultimate. The GB202 graphics processor is a large chip with a die area of 750 mm² and 92,200 million transistors. It features 24064 shading units, 752 texture mapping units, and 192 ROPs. Also included are 752 tensor cores which help improve the speed of machine learning applications. The card also has 188 raytracing acceleration cores. NVIDIA has paired 96 GB GDDR7 memory with the RTX PRO 6000 Blackwell Max-Q, which are connected using a 512-bit memory interface. The GPU is operating at a frequency of 1590 MHz, which can be boosted up to 2288 MHz, memory is running at 1750 MHz (28 Gbps effective).
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Benchmarks 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
Benchmarks
llama.cpp, llama 7B Q4_0
Geekbench AI, FP16
Geekbench AI, INT8
Geekbench AI, FP32
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
