The Gigabyte GeForce RTX 3060 Ti Gaming OC Pro is the company's premium custom-design graphics card based on NVIDIA's new GeForce RTX 3060 Ti "Ampere" GPU being launched today. Gigabyte brings to the table its iconic WindForce 3X cooling solution, RGB Fusion illumination, and a custom-design PCB geared toward overclocking. The meaty triple-slot, triple-fan cooling solution is surplus to the cooling requirements of the 200 W RTX 3060 Ti, and so it trades this surplus in for low noise. The RTX 3060 Ti "Ampere" is designed to cater to the widest gaming audience yet with its starting price of $400, enabling 1440p gaming with RTX raytracing. In addition, it's designed to play 1080p games at high refresh-rates of 144 Hz.
NVIDIA's design goal with the Ampere architecture has been to vastly improve raytracing performance over the previous generation, essentially making RTX-enabled gaming at the advertised framerate possible. The company is extensively marketing the RTX 3060 Ti as the previous-generation RTX 2080 Super, a $700 graphics card for this exact use case, at a much lower starting price of $400. The GeForce Ampere architecture heralds NVIDIA's 2nd generation RTX real-time raytracing technology that combines traditional raster 3D with raytraced elements, such as lighting, reflections, shadows, and global illumination.
The GeForce RTX 3060 Ti is based on the same 8 nm GA104 silicon as the recently launched RTX 3070. NVIDIA enables 38 out of 48 streaming multiprocessors physically present on the GPU, amounting to 4,864 Ampere CUDA cores, 152 Tensor Cores, 38 RT cores, 152 TMUs, and 80 ROPs. It comes with the same 8 GB of 14 Gbps GDDR6 memory as the RTX 3070 over the same 256-bit wide memory bus. The 2nd generation RTX technology combines new Ampere CUDA cores that offer concurrent FP32+INT32 math capability with 2nd generation RT cores, which offer higher performance, along with new hardware that enables raytraced motion blur; and the new 3rd generation Tensor core that leverages the sparsity phenomenon in deep-learning neural nets to improve AI inference performance significantly. NVIDIA leverages AI for its RTX denoiser and its DLSS performance enhancement.
As mentioned, the Gigabyte RTX 3060 Ti Gaming OC Pro features the latest generation of the company's WindForce 3X cooling solution with a compound aluminium fin-stack heatsink and trio of fans optimized for low lateral turbulence, and since the card is longer than the PCB, much of the airflow from one of the fans flows through the card and out of vents on the backplate. Gigabyte has overclocked the RTX 3060 Ti Gaming OC Pro to 1770 MHz, compared to the 1665 MHz reference. In this review, we put the card through its paces to see whether we have a new 1440p performance champion. Just like last time, Gigabyte hasn't responded to our "pricing?" email yet. Their RTX 3070 Gaming OC Pro had an MSRP of $570, or +$70 over reference, a 12% increase. So I'll use $450 throughout this review, but will update once we have more information on pricing.
GeForce RTX 3060 Ti Market Segment Analysis
Price
Shader Units
ROPs
Core Clock
Boost Clock
Memory Clock
GPU
Transistors
Memory
RTX 2060
$300
1920
48
1365 MHz
1680 MHz
1750 MHz
TU106
10800M
6 GB, GDDR6, 192-bit
RX 5700
$330
2304
64
1465 MHz
1625 MHz
1750 MHz
Navi 10
10300M
8 GB, GDDR6, 256-bit
GTX 1080
$330
2560
64
1607 MHz
1733 MHz
1251 MHz
GP104
7200M
8 GB, GDDR5X, 256-bit
RTX 2060 Super
$380
2176
64
1470 MHz
1650 MHz
1750 MHz
TU106
10800M
8 GB, GDDR6, 256-bit
RX Vega 64
$400
4096
64
1247 MHz
1546 MHz
953 MHz
Vega 10
12500M
8 GB, HBM2, 2048-bit
GTX 1080 Ti
$650
3584
88
1481 MHz
1582 MHz
1376 MHz
GP102
12000M
11 GB, GDDR5X, 352-bit
RX 5700 XT
$370
2560
64
1605 MHz
1755 MHz
1750 MHz
Navi 10
10300M
8 GB, GDDR6, 256-bit
RTX 2070
$340
2304
64
1410 MHz
1620 MHz
1750 MHz
TU106
10800M
8 GB, GDDR6, 256-bit
RTX 2070 Super
$450
2560
64
1605 MHz
1770 MHz
1750 MHz
TU104
13600M
8 GB, GDDR6, 256-bit
Radeon VII
$680
3840
64
1802 MHz
N/A
1000 MHz
Vega 20
13230M
16 GB, HBM2, 4096-bit
RTX 2080
$600
2944
64
1515 MHz
1710 MHz
1750 MHz
TU104
13600M
8 GB, GDDR6, 256-bit
RTX 2080 Super
$690
3072
64
1650 MHz
1815 MHz
1940 MHz
TU104
13600M
8 GB, GDDR6, 256-bit
RTX 3060 Ti
$400
4864
80
1410 MHz
1665 MHz
1750 MHz
GA104
17400M
8 GB, GDDR6, 256-bit
Gigabyte RTX 3060 Ti Gaming OC Pro
$450
4864
80
1410 MHz
1770 MHz
1750 MHz
GA104
17400M
8 GB, GDDR6, 256-bit
RTX 2080 Ti
$1000
4352
88
1350 MHz
1545 MHz
1750 MHz
TU102
18600M
11 GB, GDDR6, 352-bit
RTX 3070
$500
5888
96
1500 MHz
1725 MHz
1750 MHz
GA104
17400M
8 GB, GDDR6, 256-bit
RX 6800
$580
3840
96
1815 MHz
2105 MHz
2000 MHz
Navi 21
23000M
16 GB, GDDR6, 256-bit
RX 6800 XT
$650
4608
128
2015 MHz
2250 MHz
2000 MHz
Navi 21
23000M
16 GB, GDDR6, 256-bit
RTX 3080
$700
8704
96
1440 MHz
1710 MHz
1188 MHz
GA102
28000M
10 GB, GDDR6X, 320-bit
Packaging
The Card
The Gigabyte RTX 3060 Ti Gaming OC Pro is a very long design using standard PCIe-slot height, which will be useful in height-limited cases. The cooler shroud and backplate are made out of plastic.
Dimensions of the card are 29 x 11.5 cm, and it weighs 964 g.
Installation requires three slots in your system.
Display connectivity options include two standard DisplayPort 1.4a and two HDMI 2.1. Interestingly, the USB-C port for VR headsets, which NVIDIA introduced on the Turing Founders Editions, has been removed—guess it didn't take off as planned. The DisplayPort 1.4a outputs support Display Stream Compression (DSC) 1.2a, which lets you connect 4K displays at 120 Hz and 8K displays at 60 Hz. Ampere can drive two 8K displays at 60 Hz with just one cable per display.
Ampere is the first GPU to support HDMI 2.1, which increases bandwidth to 48 Gbps to support higher resolutions, like 4K144 and 8K30, with a single cable. With DSC, this goes up to 4K240 and 8K120. NVIDIA's new NVENC/NVDEC video engine is optimized to handle video tasks with minimal CPU load. The highlight here is added support for AV1 decode. Just like on Turing, you may also decode MPEG-2, VC1, VP8, VP9, H.264, and H.265 natively, at up to 8K@12-bit.
The encoder is identical to Turing. It supports H.264, H.265, and lossless at up to 8K@10-bit.
Unlike the Founders Edition, which uses the NVIDIA 12-pin power connector, Gigabyte uses standard PCIe power plugs. The card uses one 8-pin and one 6-pin power input, which are specified to provide up to 300 W combined.
Gigabyte is including a dual-BIOS feature with their card. You may switch to the silent BIOS for reduced noise output. Looks like the backplate was designed by a different team than the PCB—there's quite some distance between the label and the switch.
The GeForce RTX 3060 Ti does not support SLI. Only the RTX 3090 has very limited SLI support.
Teardown
Gigabyte's thermal solution uses five heatpipes. The main heatsink not only cools the GPU, but also provides cooling for memory chips and VRM circuitry.
The backplate is made out of metal and protects the card against damage during installation and handling. Note how Gigabyte included a modular power plug assembly here. It can easily be swapped out for a dual 8-pin, or anything else for other cards using the same PCB design.
High-resolution PCB Pictures
These pictures are for the convenience of volt modders and people who would like to see all the finer details on the PCB. Feel free to link back to us and use these in your articles or forum posts.
High-res versions are also available (front, back).