NVIDIA GeForce RTX 3060 12 GB

NVIDIA GeForce RTX 3060 12 GB
$329.00
Brand: NVIDIA
Category: GPU Benchmarks
  • Graphics Processor: GA106
  • TMUs: 112
  • Memory Type: GDDR6
  • Bus Width: 192 bit
  • ROPs: 48

SpecsByte Rating

Official Specs Rating: "Expert evaluation based on authentic manufacturer specifications and detailed product datasheets."

7.2
  • Gaming 5 / 10
  • Memory and Bandwidth 8 / 10
  • Power Consumption 8 / 10
  • Performance 8 / 10
  • Temperature and Noise 6 / 10
  • Value for money 8 / 10

NVIDIA GeForce RTX 3060 12 GB Specifications

NVIDIA released the GeForce RTX 3060 12 GB, a performance-segment graphics card, on January 12, 2021. Developed using the 8 nm technology and the GA106 graphics processor as its foundation, With a maximum power consumption rating of 170 W, the NVIDIA GeForce RTX 3060 12 GB is a dual-slot card that uses a single 12-pin power connection. Three DisplayPort 1.4a and one HDMI 2.1 display output are available.

Additionally, there are 28 raytracing acceleration cores on the GPU. Using a 192-bit memory interface, NVIDIA has combined the GeForce RTX 3060 with 12 GB of GDDR6 memory. Memory operates at 1875 MHz (15 Gbps effective), while the GPU operates at 1320 MHz, with the potential to increase to 1777 MHz. There are two cooling slots on this card, which is 242 mm long and 112 mm wide. When it first came out, it cost $329 USD.

The GA106 graphics processor has 12,000 million transistors and a die area of 276 mm², making it a chip of ordinary size. In order to meet the product’s shader objective, NVIDIA deactivated certain shading units on the GeForce RTX 3060 12 GB, in contrast to the fully unlocked GeForce RTX 3060 3840SP, which utilises the same GPU but has all 3840 shaders enabled. 48 ROPs, 112 texture mapping units, and 3584 shading units are all included. Additionally included are 112 tensor cores, which aid in accelerating machine learning applications.

Specifications

BASIC GPU INFO

GPU name GA106
Manufacturer NVIDIA
Released date Feb 25th, 2021
Launch price $329
Foundry Samsung
Architecture Ampere
Generation GeForce 30
Production Available
Successor GeForce 40
Predecessor GeForce 20

BOARD DESIGN

TDP 170 W
Slot width Dual-slot
Power connectors 1x 12-pin
Length 242 mm 9.5 inches
Height N/A
Width 112 mm 4.4 inches
Outputs 1x HDMI 2.1 3x DisplayPort 1.4a
Board number PG190 SKU 60
PSU 450 W
Bus interface PCIe 4.0 x16

GRAPHICS PROCESSING UNIT

Base clock PCIe 4.0 x16
Boost clock 1777 MHz
Transistors 12,000 million
Process size 8 nm
Process type N/A
Die size 276 mm²
MCD Die density N/A
Chip package BGA-2713
Density 43.5M / mm²

GPU MEMORY

Memory type GDDR6
Memory size 12 GB
Memory bus 192 bit
Bandwidth 360.0 GB/s
Memory clock 1875 MHz 15 Gbps
Memory speed N/A

GRAPHICS FEATURES (API)

Vulkan 1.3
DirectX 12 Ultimate (12_2)
OpenGL 4.6
OpenCL 3.0
Shader model 6.8
CUDA 8.6

CONFIGURATION

ROPs 48
Shading units 3584
TMUs 112
RT Cores 28
L1 cache 128 KB (per SM)
L2 cache 3 MB

GPU PERFORMANCE

Pixel rate 85.30 GPixel/s
Texture rate 199.0 GTexel/s
FP16 (half) 12.74 TFLOPS (1:1)
FP32 (float) 12.74 TFLOPS
FP64 (double) 199.0 GFLOPS (1:64)

Share your thoughts

  • Be the first to add a Review

    Please post a user review only if you have / had this product.

Disclaimer Note

We can not guarantee that the information on this page is 100% correct.

Back to top button