The Nvidia GeForce GTX 1070 is the second fastest Pascal based graphics card in mid May 2016. It comes in two variants, the desktop version (see here for the detail page) with 1920 shaders and the mobile variant with 2048 shaders and lower clock rates. Both cards are based on a cut down GP104 chip (like the GTX 1080) and are manufactured in 16 nm FinFET at TSMC.
Compared to the GTX1080, the GTX1070 features less CUDA cores (2048 versus 2560) that are clocked a bit lower (maximum Boost 1645 versus 1733). Instead of the new GDDR5X, the GTX 1070 uses slower GDDR5 graphics memory - but still 8 GB. The TDP is also reduced and rumored to be 10 Watts higher than the predecessor, the GTX 980M.
For thin and light laptops Nvidia offer a Max-Q called version of the GTX 1070 with lower TDP and also significantly lower performance. Sadly this variant im sold with the same GTX 1070 name, making it hard to judge the performance.
The performance depends on the cooling solution of the laptop. With a good fan system, the performance of the laptop version is on par with the desktop GTX 1070 (Founders Edition). Nvidia claims that partner solutions can be up to 10 percent slower however. In our benchmarks with various laptops the performance ranged from -5 to -14% slower performance compared to partner models of the GTX 1080 desktop models with slightly higher clocks.
On average the GTX 1070 is around 20 percent faster than the old mobile GeForce GTX 980 and therefore the second fastest mobile graphics card (non SLI). Therefore it is capable of WQHD and 4K gaming in high settings (see game benchmarks below).
The GP104 chip is manufactured in 16nm FinFET process at TSMC and offers a range of new features. DisplayPort 1.4 (ready), HDMI 2.0b, HDR, Simultaneous Multi-Projection (SMP), improved H.265 video en- and decoders (for PlayReady 3.0) are only some of the improvements. See our detailed Pascal architecture article for more details.
The power consumption of the GTX 1070 is specified with 115 Watt TGP according to Nvidia and therefore slightly above the old GeForce GTX 980M. This leads to rather big and clunky gaming laptops that use the GTX 1070. The later released Max-Q version of the GTX 1070 uses only 80 - 90 Watt TGP and is therefore better suited for thin and light laptops.
The Nvidia GTX 1050 is a mainstream GPU based on the Pascal architecture and was announced in January 2017. Contrary to the faster models, the GTX 1050 uses the GP107 chip, which is manufactured in a 14 nm process at Samsung.
The notebook version differs a bit in terms of clocks, but is equipped with 640 shader units, just like the desktop model. It is shipped with up to 4 GB GDDR5-VRAM attached via 128-bit interface and a 7 Gbps memory data rate (112 GB/s).
The GP107 chip is manufactured in a 14 nm FinFET process at Samsung and offers a number of new features, including support for DisplayPort 1.4 (ready), HDMI 2.0b, HDR, Simultaneous Multi-Projection (SMP) as well as improved H.265 video de- and encoding (PlayReady 3.0). A full list of improvements and the new Pascal desktop GPUs is available in our dedicated Pascal architecture article.
The performance of the GeForce GTX 1050 can vary quite a lot depending on the cooling performance of the laptop. It can be just as fast as the desktop model under ideal conditions, but the notebook model is usually a bit slower. The GeForce GTX 960M is beaten by around 30%, so the GTX 1050 is comparable to a GTX 965M in general. It is therefore an upper mainstream GPU. Games from 2016 can be played in high settings an the Full HD resolution.
The power consumption of the GeForce GTX 1050 is roughly on par with the old GTX 960M, which would mean around 40-50 Watts and (probably due to better selection and optimized parts) therefore much lower compared to the desktop counterpart. This means the graphics card will usually be used for powerful multimedia notebooks and entry-level gaming systems with at least 15.4 inches.
The Nvidia GeForce GTX 1060 with the Max-Q design is a mobile high-end GPU from the Pascal series. It is designed for thin and light laptops and about 10-15% slower than a regular GTX 1060 for laptops based on the cooling capabilities. The base frequency (1063-1265 MHz) is also much lower than on the regular GTX 1060 (1506 MHz, at least -16%) and the Boost (1341-1480 MHz) is also much lower compared to 1708 MHz (at least -13%) for the regular GTX 1060. The memory clock, however, is identical.
The clock is not the only difference compared to the regular GTX 1060 though. The drivers for the Max-Q version were optimized for efficiency (and not performance; only for Max-Q models), there are optimized voltage converters for 1V operation, high-end cooling methods, and a 40 dB limit for the fan noise (with clock adjustments to ensure this at all times).
The GP106 chip is produced in 16nm FinFET at TSMC and offers a range of new features, like DisplayPort 1.4 (ready), HDMI 2.0b, HDR, Simultaneous Multi-Projection (SMP) and improved H.265 video de- and encoding (PlayReady 3.0). A list of improvements and features can be found in our article on the Pascal architecture.
The power consumption of the Max-Q design is notably lower than the normal GTX 1060 for laptops and ranges between 60 and 70 Watt (TGP) according to Nvidia.