NVIDIA GeForce RTX 3060 Ti vs NVIDIA GeForce RTX 4070 Laptop GPU vs NVIDIA GeForce RTX 3060

NVIDIA GeForce RTX 3060 Ti

The Nvidia GeForce RTX 3060 Ti is a fast desktop graphics card based on the Ampere architecture. It uses the big GA104 chip and offers 4,864 cores and 8 GB GDDR6 graphics memory. 

The performance in games and 4k resolution is slightly above a desktop RTX 2080 Super. For many games, the performance is sufficient for 4k and maximum details. Enabling raytracing however (without DLSS) will lead to a significant lower performance (although the RTX performance was clearly improved compared to the RTX 2000 series).

The GA104 chip is produced in 8nm at Samsung and the power consumption of the RTX 3060 Ti is specified with 200 Watt (RTX 2070 Super - 215 Watt).

NVIDIA GeForce RTX 4070 Laptop GPU

The NVIDIA GeForce RTX 4070 Laptop GPU (Codename GN21-X6) is a high-end laptop GPU. It is based on the AD106 chip and use the Ada Lovelace architecture. The RTX 4070 offers 4,608 cores (of the 7,680 in the AD106) and a 128 Bit memory bus. The RTX 4070 mobile uses 8 GB GDDR6 dedicated graphics memory with a clock speed of 16 Gbps (effective). The TGP (Total Graphics Power) can be configured between 35 and 115 Watt (+ 15-25 Watt Dynamic Boost from the CPU) leading to different performance levels (the desktop RTX 4070 Ti uses 285 Watt for comparisons). The boost clock speed ranges from 1230 MHz (at 35 Watt TGP) up to 2175 MHz (115W). Therefore, the performance is also depending a lot on the power setting used for the RTX 4080 mobile in the laptop.

The performance should be below the desktop RTX 4070 Ti and therefore best suited for 2k and maximum details for demanding games of 2022.

Our synthetic benchmarks of an average RTX 4070 mobile show a performance slightly below a mobile RTX 3080 Ti. However, with reduced power limits, the performance is clearly suffering, e.g. only 70% in Time Spy for a version with 60W TDP. In games, a fast RTX 4070 is best suited for QHD gaming, where some very demanding games wont reach the 60 fps limit (and may have to run at 1080p, reduced settings or using DLSS). See below for detailed gaming benchmarks of various cards.

The RTX 4070 offers 144 tensor cores (4th gen) that enable DLSS 3 including frame generation for supported games. Furthermore, 36 raytracing cores (4rd gen) can be used for raytracing effects in supported games.

The AD106 chip is manufactured in 5nm at TSMC (4N process).

NVIDIA GeForce RTX 3060

The Nvidia GeForce RTX 3060 is a fast desktop graphics card. It is based on the GA106 Ampere chip and offers 12 GB GDDR6 graphics memory with a 192 Bit memory bus. It offers 3,584 cores and supports PCIe 4.0.

The performance is similar to the older GeForce RTX 2070 and therefore best suited for 1080p gaming of modern and demanding games in high settings.

The GA106 chip offers 3,840 FP32 ALUs of which half can also execute INT32 instructions (i.e. 1,920 INT32 ALUs). With Turing all shaders could still execute FP32 or INT32 instructions. The raytracing and tensor cores on the chip were also improved according to Nvidia. The Ampere chips also include an improved 5th generation video encoder (NVENC for H.264 and H.265) and a 7th generation decoder (for various formats now including AV1).

The GA106 chip is manufactured by Samsung in 8nm (8N), which is not quite able to keep up with the 7nm node at TSMC (e.g. used by AMD and also for the professional GA100 Ampere chip). The TDP of the RTX 3060 is specified at 170 Watt and therefore slightly higher than the previous RTX 2060 (160 Watt).