GPUDesktopReleased —

NVIDIA GeForce RTX 3060 OEM

192-bit · 3,840 cores

This is a variant of the GeForce RTX 3060 built on the fully enabled GA106 GPU, with all 30 streaming multiprocessors active for 3,840 CUDA cores instead of the 3,584 of the retail card, and a higher 1,627 MHz base clock. NVIDIA never officially announced it; it has been found only in some OEM systems and in a board-partner BIOS dated December 2020, and its memory configuration and power rating were never officially published.

General

Manufacturer: NVIDIA
Model: GeForce RTX 3060 OEM
Segment: Desktop
GPU chip: GA106
Architecture: Ampere
Release date: —
Price: Search on Amazon

Memory

Memory size: —
Memory type: GDDR6
Bus width: 192-bit
Bandwidth: —
Memory clock: —

Clocks & silicon

GPU clock: 1,627 MHz
Boost clock: —
Shader units: 3,840 CUDA Cores
Tensor / AI cores: 120
RT cores: 30
Transistors: 12 billion
Technology (nm): 8 nm
Samsung 8 nm (8N)
TDP / TBP: —

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

AI support

Precisions: FP8FP16BF16INT8INT4TF32FP64
AI accelerator: 3rd Gen Tensor Cores (120) + 2nd Gen RT Cores (30)
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 →

Desktop gpus from NVIDIA announced around the same time as the NVIDIA GeForce RTX 3060 OEM. Add any of them to your compare list to see the specs side by side.

gpu