GPUWorkstationReleased Aug 13, 2018

NVIDIA Quadro RTX 5000

16 GB GDDR6 ECC · 256-bit · 3,072 cores

A Turing-based professional workstation card announced at SIGGRAPH in August 2018 with the Quadro RTX 6000 and 8000, bringing RT Cores for hardware ray tracing and Tensor Cores for AI to NVIDIA's mid-to-high-end Quadro line. It uses the full TU104 chip with 16 GB of ECC-capable GDDR6, and two cards can be joined with an NVLink bridge to pool 32 GB of memory. It also offers a VirtualLink USB-C port for VR headsets.

General

Manufacturer: NVIDIA
Model: Quadro RTX 5000
Segment: Workstation
GPU chip: TU104-875
Architecture: Turing
Release date: Aug 13, 2018
Price: Search on Amazon

Memory

Memory size: 16 GB
Memory type: GDDR6 ECC
Bus width: 256-bit
Bandwidth: 448 GB/s
Memory clock: 1,750 MHz

Clocks & silicon

GPU clock: 1,620 MHz
Boost clock: 1,815 MHz
Shader units: 3,072 CUDA Cores
Tensor / AI cores: 384
RT cores: 48
Transistors: 13.6 billion
Technology (nm): 12 nm
TSMC 12 nm FFN
TDP / TBP: 265 W

Interface & APIs

Bus interface: PCIe 3.0 x16
SLI / multi-GPU: NVLink (2-way bridge)
DirectX: 12 Ultimate (12_2)
OpenGL: 4.6
Vulkan: 1.4
Other APIs: CUDA (Compute Capability 7.5), OpenCL 3.0

AI support

Precisions: FP8FP16BF16INT8INT4TF32FP64
AI accelerator: 2nd Gen Tensor Cores (384) + 1st Gen RT Cores (48)
Peak AI TOPS: —
Notes: 2nd-gen Tensor Cores. FP16/INT8/INT4 supported; no BF16, TF32 or FP8 on Turing. FP64 at 1/32 rate.

All NVIDIA GPUs →

Workstation gpus from NVIDIA announced around the same time as the NVIDIA Quadro RTX 5000. Add any of them to your compare list to see the specs side by side.

gpu