GPUWorkstationReleased Feb 12, 2024

NVIDIA RTX 2000 Ada Generation

16 GB GDDR6 ECC · 128-bit · 2,816 cores

The RTX 2000 Ada Generation is NVIDIA's entry Ada workstation card, launched on February 12, 2024 as the successor to the RTX A2000. It keeps the compact low-profile, dual-slot body and slot-only 70 W power draw, so it fits small-form-factor and OEM desktops without an auxiliary power connector, while raising memory to 16 GB of ECC GDDR6. It adds AV1 encoding and DLSS 3 for content creation, CAD and edge AI workloads.

General

Manufacturer: NVIDIA
Model: RTX 2000 Ada Generation
Segment: Workstation
GPU chip: AD107-875
Architecture: Ada Lovelace
Release date: Feb 12, 2024
Price: Search on Amazon

Memory

Memory size: 16 GB
Memory type: GDDR6 ECC
Bus width: 128-bit
Bandwidth: 224 GB/s
Memory clock: 1,750 MHz

Clocks & silicon

GPU clock: 1,620 MHz
Boost clock: 2,130 MHz
Shader units: 2,816 CUDA Cores
Tensor / AI cores: 88
RT cores: 22
Transistors: 18.9 billion
Technology (nm): 5 nm
TSMC 4N (5 nm-class)
TDP / TBP: 70 W

Interface & APIs

Bus interface: PCIe 4.0 x8
SLI / multi-GPU: None (no SLI / NVLink)
DirectX: 12 Ultimate (12_2)
OpenGL: 4.6
Vulkan: 1.4
Other APIs: CUDA 8.9, OpenCL 3.0, DLSS 3

AI support

Precisions: FP8FP16BF16INT8INT4TF32FP64
AI accelerator: 4th Gen Tensor Cores (88) + 3rd Gen RT Cores (22)
Peak AI TOPS: 191.9 TOPS
Notes: 4th-gen Tensor Cores with FP8 Transformer Engine. NVIDIA rates tensor performance at 191.9 TFLOPS (FP8, with sparsity). FP64 at 1/64 rate.

All NVIDIA GPUs →

Workstation gpus from NVIDIA announced around the same time as the NVIDIA RTX 2000 Ada Generation. Add any of them to your compare list to see the specs side by side.

gpu