Report an Error

NVIDIA GeForce RTX 3060 Ti

Graphics Processor
GA104
Cores
4864
TMUs
152
ROPs
80
Memory Size
8 GB
Memory Type
GDDR6
Bus Width
256 bit
This product is not released yet.
Data on this page may change in the future.
The GeForce RTX 3060 Ti will be a graphics card by NVIDIA, that is expected to launch in 2020. Built on the 8 nm process, and based on the GA104 graphics processor, in its GA104-200-A1 variant, the card supports DirectX 12 Ultimate. This ensures that all modern games will run on GeForce RTX 3060 Ti. Additionally, the DirectX 12 Ultimate capability guarantees support for hardware-raytracing, variable-rate shading and more, in upcoming video games. The GA104 graphics processor is a large chip with a die area of 392 mm² and 17,400 million transistors. Unlike the fully unlocked GeForce RTX 3070 Ti, which uses the same GPU but has all 6144 shaders enabled, NVIDIA has disabled some shading units on the GeForce RTX 3060 Ti to reach the product's target shader count. It features 4864 shading units, 152 texture mapping units, and 80 ROPs. Also included are 152 tensor cores which help improve the speed of machine learning applications. The card also has 38 raytracing acceleration cores. NVIDIA has paired 8 GB GDDR6 memory with the GeForce RTX 3060 Ti, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 1410 MHz, which can be boosted up to 1665 MHz, memory is running at 1750 MHz (14 Gbps effective).
Being a dual-slot card, the NVIDIA GeForce RTX 3060 Ti draws power from 1x 12-pin power connector, with power draw rated at 200 W maximum. Display outputs include: 1x HDMI, 3x DisplayPort. GeForce RTX 3060 Ti is connected to the rest of the system using a PCI-Express 4.0 x16 interface. The card measures 242 mm in length, 112 mm in width, and features a dual-slot cooling solution.

Graphics Processor

GPU Name
GA104
GPU Variant
GA104-200-A1
Architecture
Ampere
Foundry
Samsung
Process Size
8 nm
Transistors
17,400 million
Die Size
392 mm²

Graphics Card

Release Date
2020
Availability
2020
Generation
GeForce 30
Production
Unreleased
Bus Interface
PCIe 4.0 x16

Relative Performance

1%
GeForce 210
1%
GeForce 9400 GT
2%
Radeon HD 4550
2%
Radeon HD 5450
3%
Radeon HD 6450
3%
GeForce GT 520
3%
GeForce GT 220
5%
GeForce GT 430
5%
Radeon HD 5570
5%
Radeon HD 4670
5%
GeForce GT 440
5%
GeForce GT 240
6%
GeForce 9600 GT
7%
Radeon HD 5670
7%
GeForce GT 640
7%
GeForce 9800 GT
8%
Radeon HD 6670
8%
Radeon HD 4830
8%
Radeon HD 4770
9%
Radeon HD 4850
9%
GeForce GTS 250
9%
GeForce GTS 450
10%
Radeon HD 5750
11%
Radeon HD 7750
11%
Radeon HD 5770
11%
GeForce GTX 260
11%
Radeon HD 4870
11%
Radeon Vega 8
12%
GeForce GTX 550 Ti
12%
GeForce GTX 650
12%
Radeon HD 5830
13%
Radeon HD 6790
13%
Radeon HD 4890
14%
GeForce GTX 460
14%
Radeon RX Vega 11
14%
GeForce GT 1030
14%
GeForce GTX 275
14%
Radeon HD 7770 GHz Edition
14%
GeForce GTX 280
14%
GeForce GTX 465
15%
Radeon HD 6850
15%
GeForce GTX 285
16%
Radeon HD 5850
17%
GeForce GTX 650 Ti
17%
Radeon HD 7790
17%
Radeon RX 550
17%
GeForce GTX 470
18%
Radeon HD 6870
19%
Radeon HD 5870
20%
GeForce GTX 560 Ti
20%
Radeon HD 4870 X2
20%
GeForce GTX 750 Ti
21%
Radeon HD 6950
21%
GeForce GTX 295
21%
GeForce GTX 650 Ti Boost
22%
Radeon HD 7850
22%
GeForce GTX 480
23%
Radeon HD 6970
23%
Radeon R7 265
24%
Radeon RX 460
24%
Radeon R7 370
24%
GeForce GTX 660
24%
GeForce GTX 570
24%
Radeon RX 560
26%
GeForce GTX 950
26%
Radeon HD 7870 GHz Edition
27%
Radeon R9 270X
27%
GeForce GTX 660 Ti
27%
GeForce GTX 580
27%
GeForce GTX 1050
28%
Radeon HD 7950
28%
Radeon HD 5970
29%
GeForce GTX 760
31%
GeForce GTX 670
32%
GeForce GTX 960
33%
Radeon R9 380
33%
Radeon R9 285
33%
Radeon HD 7970
34%
GeForce GTX 680
34%
GeForce GTX 1050 Ti
35%
GeForce GTX 770
36%
Radeon HD 6990
37%
Radeon R9 280X
37%
GeForce GTX 590
37%
Radeon HD 7970 GHz Edition
41%
GeForce GTX 780
43%
GeForce GTX 1650
46%
Radeon RX 470
46%
Radeon R9 290
49%
Radeon RX 570
49%
Radeon R9 390
50%
Radeon R9 290X
50%
GeForce GTX 970
51%
GeForce GTX TITAN
52%
GeForce GTX 780 Ti
52%
Radeon R9 390X
53%
Radeon HD 7990
53%
Radeon RX 480
53%
GeForce GTX 690
55%
GeForce GTX 1060 6 GB
56%
Radeon RX 5500 OEM
56%
Radeon RX 580
57%
Radeon RX 5500 XT
57%
GeForce GTX 980
58%
GeForce GTX 1650 SUPER
58%
Radeon R9 FURY
61%
Radeon RX 590
64%
Radeon R9 295X2
64%
GeForce GTX 1660
65%
Radeon R9 FURY X
66%
GeForce GTX 980 Ti
68%
GeForce GTX TITAN X
72%
GeForce GTX 1660 SUPER
74%
GeForce GTX 1660 Ti
74%
GeForce GTX 1070
79%
Radeon RX Vega 56
83%
GeForce GTX 1070 Ti
86%
Radeon RX Vega 64
87%
GeForce RTX 2060
87%
GeForce GTX 1080
90%
Radeon RX 5700
98%
GeForce RTX 2060 SUPER
100%
GeForce RTX 3060 Ti
101%
GeForce RTX 2070
104%
Radeon RX 5700 XT
105%
Radeon VII
107%
TITAN X Pascal
111%
GeForce GTX 1080 Ti
112%
GeForce RTX 2070 SUPER
119%
GeForce RTX 2080
126%
GeForce RTX 2080 SUPER
139%
GeForce RTX 2080 Ti
184%
GeForce RTX 3080
217%
GeForce RTX 3090
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

Base Clock
1410 MHz
Boost Clock
1665 MHz
Memory Clock
1750 MHz
14 Gbps effective

Memory

Memory Size
8 GB
Memory Type
GDDR6
Memory Bus
256 bit
Bandwidth
448.0 GB/s

Render Config

Shading Units
4864
TMUs
152
ROPs
80
SM Count
38
Tensor Cores
152
RT Cores
38
L1 Cache
128 KB (per SM)
L2 Cache
4 MB

Theoretical Performance

Pixel Rate
133.2 GPixel/s
Texture Rate
253.1 GTexel/s
FP16 (half) performance
16.20 TFLOPS (1:1)
FP32 (float) performance
16.20 TFLOPS
FP64 (double) performance
253.1 GFLOPS (1:64)

Board Design

Slot Width
Dual-slot
Length
242 mm
9.5 inches
Width
112 mm
4.4 inches
TDP
200 W
Suggested PSU
350 W
Outputs
1x HDMI
3x DisplayPort
Power Connectors
1x 12-pin
Board Number
PG190 SKU 20

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
2.0
Vulkan
1.2
CUDA
8.5
Shader Model
6.5

GA104 GPU Notes

Speculation