This year’s NVIDIA mobile GPUs are deliberately named after their desktop counterparts and miss the M at the back. And the reason is obvious, NVIDIA wants you to believe that they’ve finally closed the performance gap between two form factors – mobile and desktop. However, as our gaming and synthetic benchmarks show, this isn’t exactly true. There’s a little more way to go but it’s closer than ever and definitely closer than Maxwell was.
Put side by side, both variants seem almost identical but small details make the whole difference. For instance, the mobile GTX 1070 features a tad more CUDA cores and Texture Mapping Units (TMUs) than the desktop version (2048 vs 1920 and 170 vs 120 for CUDA and TMU respectively) but its core is clocked slightly lower – 1443 – 1645 MHz vs 1506 – 1683 MHz. The latter probably makes the biggest difference in the testing. But, on the other hand, when we did a short stress test of the mobile GPU, GPU-Z didn’t register clock rates above 1556 MHz so the pre-production sample not utilizing the full potential of the graphics card might also have to do with the tests’ outcome.
Nonetheless, the rest of the specs are identical, including the memory specs (8GB GDDR5 VRAM clocked at 2000 MHz on a 256-bit bus). That’s why in real-life use (gaming tests) the difference isn’t as big, only around 8-10% according to maxed out Full HD settings in F1, Tomb Raider, HITMAN, GTA V and Middle-Earth: Shadow of Mordor.
But how does it stack against its older predecessor 970M?
To be honest, this question needs to be paraphrased like this: “How does it stack against real predecessor, the GTX 980?”. Why? It’s simple. According to the early benchmarks and gaming tests , the GTX 1060 is a successor to the 970, the GTX 1070 to the 980 and 1080 to the 980 Ti. That’s why the early adoption of the GTX 1070 in laptops makes them so absurdly expensive. That’s because you get a top-notch desktop-like GPU performance without sacrificing portability. So if you are still waiting for the affordable Pascal GPUs, you might want to wait for the rumored GTX 1050 Ti GPU or maybe the 1060 as well.
Anyway, below you will see a comparison between the GTX 980 (Laptop), 970M, and desktop 1070 to get a better grasp of the evolution of the NVIDIA GeForce GTX family for now.
|GPU||GeForce GTX 1070 Mobile||GeForce GTX 1070 FE||GeForce GTX 970M||GeForce GTX 980M||GeForce GTX 980 (Laptop)|
|Unigine Heaven 3.0||4160||5462 (+31%)||2299 (-45%)||2963 (-29%)||3487 (-16%)|
|Unigine Heaven 4.0||3556||4489 (+26%)||1678 (-53%)||2311 (-35%)||2586 (-17%)|
|3DMark Cloud Gate||84191||115350 (+37%)||51143 (-39%)||66709 (-21%)||76639 (-9%)|
|3DMark Sky Diver||47767||59970 (+26%)||24596 (-49%)||30780 (-34%)||40266 (-16%)|
|3Dmark Fire Strike||15485||18123 (+17%)||7429 (-52%)||9319 (-40%)||11937 (-23%)|
|GPU||Tomb Raider (1080p, Low)||Tomb Raider (1080p, Medium)||Tomb Raider (1080p, High)|
|Mobile GTX 1070||351 fps||245 fps||129 fps|
|Desktop GTX 1070||555 fps (+58%)||275 fps (+22)||136 fps (+5%)|
|GPU||F1 2015 (1080p, Low)||F1 2015 (1080p, Medium)||F1 2015 (1080p, Max)|
|Mobile GTX 1070||128 fps||110 fps||106 fps|
|Desktop GTX 1070||182 fps (+42%)||152 fps (+38%)||130 fps (+23%)|
|GPU||GTA 5 (1080p, Low)||GTA 5 (1080p, Medium)||GTA 5 (1080p, Max)|
|Mobile GTX 1070||140 fps||100 fps||48 fps|
|Desktop GTX 1070||168 fps (+20%)||131 fps (+31%)||52 fps (+8%)|
|GPU||Hitman: 2016 (1080p, Low)||Hitman: 2016 (1080p, Medium)||Hitman: 2016 (1080p, Max)|
|Mobile GTX 1070||93 fps||87 fps||75 fps|
|Desktop GTX 1070||105 fps (+13%)||98 fps (+13%)||80 fps (+7%)|
|GPU||Middle-Earth: Shadow of Mordor (1080p, Low)||Middle-Earth: Shadow of Mordor (1080p, Medium)||Middle-Earth: Shadow of Mordor (1080p, Max)|
|Mobile GTX 1070||170 fps||151 fps||121 fps|
|Desktop GTX 1070||235 fps (+38%)||189 fps (+25%)||133 fps (+10%)|
The notebooks used for this article are the ASUS ROG G752VT (with GTX 970M), the Alienware 17 R3 (with GTX 980M) and Acer Predator 17X (with GTX 980 for laptops).