Apple M2 Pro 16-Core GPU vs NVIDIA GeForce RTX 4070

Apple M2 Pro 16-Core GPU

The Apple M2 Pro 16-Core-GPU is an integrated graphics card by Apple offering all 16 of the 19 cores in the M2 Pro 10-Core Chip.

The graphics card has no dedicated graphics memory but can use the fast LPDDR5-6400 unified memory with a 256 bit bus (up to 200 GBit/s).

According to Apple, the performance of the 19-core-GPU should be 30% higher than the old 16-core-GPU in the M1 Pro. Therefore, the cut down 16-core version should still beat the old full-featured 16-core M1 Pro slightly and the old 14-core more clearly.

The GPU is intended to use Apple Metal 2 API and could still be based on the older PowerVR architectures (last used in the Apple A10). A new feature in the MacBook Pro 14 of 2023 is the support for HDMI 2.1 and 8k output.

The Apple M2 Pro is manufactured in the second generation 5nm process at TSMC.

NVIDIA GeForce RTX 4070

The Nvidia GeForce RTX 4070 is a high-end desktop graphics card based on the AD104 chip using the Ada Lovelace architecture. The 4070 offers 5,888 cores and 12 GB GDDR6X graphics memory with a 192 bit memory bus and clocked at 21 Gbits. The card offers a good raytracing performance thanks to the 46 dedicated raytracing cores. For AI calculations (and DLSS 3 in games), the RTX 4070 has 184 Tensor cores.

The gaming performance is well suited for 2k/QHD gaming in most demanding games, and should be able to handle 4k gaming for lesser demanding games (or with reduced settings / DLSS activated). The raw gaming performance is comparable to an older RTX 3080 or a AMD Radeon 6800 XT. Compared to the similar named mobile GeForce RTX 4070 Laptop GPU, the desktop variant is much faster.

The AD104 chip is manufactured in the modern 5nm process at TSMC (4N with EUV) and specified with a TGP (Total Graphics Power) of 200 Watt (compared to the 450 Watt of the RTX 4090).