Skip to main content

Digital Trends may earn a commission when you buy through links on our site. Why trust us?

Leak suggests mobile version of Nvidia’s GTX 1070 and 1060 won’t differ much from the desktop

nvidia pascal mobile gpus gtx1070 gtx1060 logo
Image used with permission by copyright holder
Now that Nvidia’s Pascal-based GeForce GTX 1070 and GTX 1060 cards are available on the market, the spotlight falls on the mobile versions of these graphics chips. While nothing official has hit the streets, reports have surfaced showing these two mobile GPUs listed separately in the GPU-Z application. So much for that rumor about scrapping high-end mobile versions for full-blown GPUs in notebooks? Perhaps not.

For starters, a screenshot provided by BenchLife shows that the mobile version of the GTX 1070 will have 2,048 CUDA cores, which is 128 more than the desktop version. There are also 64 Render Output Units, 170 Texture Memory Units, a pixel fill rate of 92.4 gigapixels per second, and a texture fill rate of 245.3 gigatexels per second. The chip is backed by 8GB of GDDR5 memory from Samsung, a 256-bit bus width, and a memory bandwidth of 256.3GB per second.

As for other details, the mobile GTX 1070 chip has a base clock speed of 1,443MHz, a boost clock speed of 1,645MHz, and a memory clock speed of 2,002MHz. Nvidia SLI is shown as disabled, and the chip shows it to be compatible with DirectCompute 5.0.

Get your weekly teardown of the tech behind PC gaming
Check your inbox!

As for the mobile version of the GTX 1060, a screenshot of the GPU-Z app provided by PurePC shows that it has 1,280 CUDA cores, the same amount offered in the desktop version. Also, there are 48 Render Output Units, 106 Texture Memory Units, a pixel fill rate of 67.4 gigapixels per second, and a texture fill rate of 148.9 gigatexels per second.

The unannounced mobile chip will supposedly have 6GB of GDDR5 memory provided by Samsung, with a 192-bit bus width and a bandwidth of 192.2GB per second. The chip’s base clock speed shows to be 1,405MHz, its boost clock speed at 1,671MHz, and its memory clock speed at 2,002MHz. Nvidia SLI is also shown to be disabled for this specific graphics chip.

Basically, the mobile GTX 1060 offers similar specs as the desktop version, but with a lower clock speed. The desktop version, launched on Tuesday, has a base clock speed of 1,506MHz and a boost clock speed of 1,709MHz. As for the mobile GTX 1070 chip, the CUDA count is higher, as previously stated, but the clock speeds are lower, as the desktop version has a base clock of 1,506MHz, and a boost clock of 1,683MHz.

As the two GPU-Z screenshots suggest, Nvidia’s Pascal architecture seemingly allows the company to cram a desktop-grade GPU into a notebook, as the previous rumor suggested. Of the two examples, the GTX 1070 is the most altered component with the added cores and reduced clock speeds, but otherwise the difference isn’t that far off…. if the GPU-Z screenshots are indeed authentic.

In addition to the GPU-Z app, PurePC shows a screenshot of a 3DMark Firestrike benchmark using the mobile GTX 1060 chip. The gaming laptop used in the test also included an Intel Core i7-6700K processor and 16GB of system memory. This laptop obtained a score of 10,295 points in the benchmark, which seems mighty impressive for a notebook with a “mobile” GPU installed.

Kevin Parrish
Former Digital Trends Contributor
Kevin started taking PCs apart in the 90s when Quake was on the way and his PC lacked the required components. Since then…
Gigabyte may have accidentally leaked Nvidia’s plans for the RTX 4080 12GB
Gigabyte's RTX 3090 Ti up close.

A new leak shows that Gigabyte is readying some new graphics cards, and both AMD and Nvidia fans have something to look forward to.

It seems that Gigabyte may have inadvertently confirmed previous rumors about Nvidia's plans in regard to the "unlaunched" RTX 4080 12GB.

Read more
The 5 worst Nvidia GPUs of all time
Fans on the Nvidia RTX 3080.

Nvidia has a strong pedigree for making great graphics cards. It has never really been the underdog and its greatest GPUs outshone those of its rival AMD time and time again. But despite Nvidia's penchant for innovation and technological advancement, it has put out quite a few abominable cards, cursed not necessarily by bad technology, but often by poor decision making. Let's reminisce on some Nvidia GPUs we wish we could forget.
GeForce GTX 480
The way it's meant to be grilled

Although Nvidia has been in business for over 20 years now, there's really only one GPU the company has ever put out that was truly terrible on a technological level, and it's the GTX 480. Powered by the Fermi architecture, the GTX 480 (and the entire 400 series by extension) was plagued by multitudes of issues which in turn allowed AMD to become the leading graphics chip maker and nearly overtake Nvidia in market share.

Read more
Nvidia RTX 4050 impresses in first benchmark leak
Nvidia-powered laptop showing Nividia components highlighted, running Red Dead Redemption.

The Nvidia GeForce RTX 4050 will almost definitely be the most affordable GPU released with the Ada Lovelace architecture but it will still pack some graphical power according to this first benchmark leak.

Someone seems to have tested an early version of the laptop version of the RTX 4050 on Puget Bench, a graphics productivity benchmark that focuses on speed tests using several popular Adobe apps. The particular app tested was Adobe Premiere Pro, one of the leading video editing apps.

Read more