GPUWorkstationReleased Aug 10, 2021

NVIDIA RTX A2000

12 GB GDDR6 ECC · 192-bit · 3,328 cores

The RTX A2000 is a compact, low-profile Ampere workstation card that draws all of its power through the slot and needs no auxiliary connector, which suits small-form-factor and OEM desktops. It was announced on August 10, 2021 as a 6 GB model and reached workstations from October 2021, and a 12 GB variant with the same core configuration followed later.

General

Manufacturer: NVIDIA
Model: RTX A2000
Segment: Workstation
GPU chip: GA106-850
Architecture: Ampere
Release date: Aug 10, 2021
Price: Search on Amazon

Memory

Memory size: 6 – 12 GB
Memory type: GDDR6 ECC
Bus width: 192-bit
Bandwidth: 288 GB/s
Memory clock: 1,500 MHz

Clocks & silicon

GPU clock: 562 MHz
Boost clock: 1,200 MHz
Shader units: 3,328 CUDA Cores
Tensor / AI cores: 104
RT cores: 26
Transistors: 12 billion
Technology (nm): 8 nm
Samsung 8N (8 nm)
TDP / TBP: 70 W

Interface & APIs

Bus interface: PCIe 4.0 x16
SLI / multi-GPU: None (no SLI / NVLink)
DirectX: 12 Ultimate (12_2)
OpenGL: 4.6
Vulkan: 1.4
Other APIs: CUDA 8.6, OpenCL 3.0, DLSS 2

AI support

Precisions: FP8FP16BF16INT8INT4TF32FP64
AI accelerator: 3rd Gen Tensor Cores (104) + 2nd Gen RT Cores (26)
Peak AI TOPS: —
Notes: 3rd-gen Tensor Cores with sparsity. TF32/BF16/FP16/INT8/INT4 supported; no FP8 on Ampere. FP64 at 1/64 rate.

All NVIDIA GPUs →

Workstation gpus from NVIDIA announced around the same time as the NVIDIA RTX A2000. Add any of them to your compare list to see the specs side by side.

gpu