NVIDIA GeForce RTX 4070 SUPER vs NVIDIA GeForce GTX 960 vs NVIDIA GeForce GTX 980 (Laptop)

NVIDIA GeForce RTX 4070 SUPER

The Nvidia GeForce RTX 4070 SUPER is a high-end desktop graphics card based on the Ada Lovelace architecture. It uses the AD104 chip and offers 7,168 cores and 12 GB GDDR6X graphics memory (192-bit bus with 21 Gbits).

The performance of the RTX 4070S lies between the older RTX 4070 and RTX 4070 Ti in the top class of high-end GPUs in 2024. Compared to AMD GPUs, the 4070 Super is similar fast as the AMD Radeon RX 7800 XT. This makes the GPU best suited for QHD and maximum details of demanding games (such as Avatar Frontiers of Pandora, Allan Wake 2, Cyberpunk 2033 or F1 23). Less demanding games can also be played smoothly in 4K (AC Mirage, Cod MW 3, ...).

The AD104 chip is produced at TSMC in 5 nm (4N with EUV) and is specified with a TGP (Total Graphics Power) of 200 watts.

NVIDIA GeForce GTX 960

The Nvidia GeForce GTX 960 is a desktop graphics card of the upper middle class. It is based on the GM206 Maxwell chip that is produced in 28nm. The GTX960 offers 1024 shader cores, 64 TMUs and 32 ROPs (no deactivated units of the chip). The graphics memory is usually 2 or 4 GB GDDR5 (7 GHz effective clock) connected with a 128 Bit interface. 

On average the gaming performance is on a level with the AMD Radeon R9 280 and R9 285. Compared to laptop graphics cards, the 960 is slightly faster than a mobile Nvidia GeForce GTX 970M. The 970M offers more shader cores, but at a lower clock speed. The similar named GeForce GTX 960M for notebooks offers only 640 shader cores and a slightly lower core clock. The performance of the GTX 960 should be suffice for most games in full HD resolution. In our benchmarks only GTA 5 and The Witcher 3 achieved below 30 fps on average (see below for detailed benchmarks).

The GM206 supports CUDA, 3D Vision, PhysX, GeForce Experience, Surround, GameStream, GPU Boost 2.0, Adaptive Vertical Sync / G-SYNC, SLI, DSR, MFAA and Virtual Reality latency improvements. The GTX 960 also includes a H.265 capable de- and encoder as a first.

The power consumption of the GTX 960 on the desktop without load is around 10 Watt and on a similar level to the AMD counterparts. During gaming the 960 reaches around 85-100 Watt (depending on the model) which is a lot less than e.g. the Radeon R9 285 (around 170 Watt) - source tomshardware.com

NVIDIA GeForce GTX 980 (Laptop)

The NVIDIA GeForce GTX 980 for notebooks (not the GTX 980M, sometimes also referred to as GeForce GTX 990M) is an overclockable high-end graphics card for laptops. It is an desktop Geforce GTX 980 chip with the same specifications (2048 shaders, 1126 MHz base clock, 7 Gbps memory) based on selected GM204 chips (for lower power consumption).

The performance is also on a level with the desktop GTX 980. Due to the different cooling solutions, the long term performance may be slightly lower compared to a well cooled desktop, but Nvidia assures only small degrades in performance. Furthermore, the mobile GTX 980 supports overclocking out of the box and all laptop manufacturers plan to provide an easy to use tool to overclock the card on the fly.

The core features are also the same, so expect support for DirectX 12 (FL 12_1). There will be no support for the new H.265 video engine as found on the desktop GTX 950.

The power consumption of the card is a lot higher than other mobile graphics card like the GeForce GTX 980M (100 Watt TDP). According to Nvidia, the TDP of the reference design is still 165 Watt like in the desktop version. Including overclocking headroom, the power consumption may reach up to 200 Watt. Therefore, only big laptops with efficient cooling methods can house the GeForce GTX980 for laptops.