GPUBoss Review Our evaluation of 970 vs 1070 Mobile among all GPUs


Battlefield 3, Battlefield 4, Bioshock Infinite and 21 more


T-Rex, Manhattan, Cloud Gate Factor, Sky Diver Factor and 1 more


Face Detection, Ocean Surface Simulation and 3 more

Performance per Watt

Battlefield 3, Battlefield 4, Bioshock Infinite and 32 more

Noise and Power

TDP, Idle Power Consumption, Load Power Consumption and 2 more

Nvidia GeForce GTX 970 

GPUBoss recommends the Nvidia GeForce GTX 970  based on its .

See full details

Cast your vote Do you agree or disagree with GPUBoss?

Thanks for adding your opinion. Follow us on Facebook to stay up to date with the latest news!

Differences What are the advantages of each

Front view of GeForce GTX 970

Reasons to consider the
Nvidia GeForce GTX 970

Report a correction

GPUBoss is not aware of any important advantages of the 970 vs the 1070 Mobile.

Front view of GeForce GTX 1070 Mobile

Reasons to consider the
Nvidia GeForce GTX 1070 Mobile

Report a correction
Significantly higher clock speed 1,442 MHz vs 1,050 MHz More than 35% higher clock speed
More memory 8,192 MB vs 4,096 MB 2x more memory
Better floating-point performance 5,906 GFLOPS vs 3,494 GFLOPS Around 70% better floating-point performance
Higher pixel rate 92.3 GPixel/s vs 58.8 GPixel/s More than 55% higher pixel rate
Significantly higher turbo clock speed 1,645 MHz vs 1,178 MHz Around 40% higher turbo clock speed
Higher texture rate 184.6 GTexel/s vs 109.2 GTexel/s Around 70% higher texture rate
Higher effective memory clock speed 8,008 MHz vs 7,012 MHz Around 15% higher effective memory clock speed
Higher memory bandwidth 256.3 GB/s vs 224.4 GB/s Around 15% higher memory bandwidth
Better fire strike factor score 87.79 vs 72.7 More than 20% better fire strike factor score
More shading units 2,048 vs 1,664 384 more shading units
More texture mapping units 128 vs 104 24 more texture mapping units
More render output processors 64 vs 56 8 more render output processors
Higher memory clock speed 2,002 MHz vs 1,753 MHz Around 15% higher memory clock speed
Lower TDP 120W vs 148W Around 20% lower TDP

Benchmarks Real world tests of GeForce GTX 970 vs 1070 Mobile

Fire Strike Factor Data courtesy FutureMark

Sky Diver Factor Data courtesy FutureMark

Cloud Gate Factor Data courtesy FutureMark


Showing 11 comments.
Actually, according to multiple benchmarks of a 1070 vs 1070'm' the difference is extremely low, not even 10-15%. From what I recall, the 1070 scored around 78FPS in The Division, and the mobile version scored 75FPS, and this not only within the margin of error (<5FPS I believe), but it could also be attributed to the weaker CPU (6700K vs 6700HQ). Once I find the benchmarks video again, I can post it here if you fancy.
while pascal notebook implementation are much closer to desktop implementations than any previous generation I'm still going to say that Ben is right on this one but no one is going to sweat the 10-15% performance drop
It's pretty different, actually. A desktop 1070 is going to offer pretty much the same performance as the 1070 seen in laptops, minus 2-3 frames. However, a desktop 980 vs a 980m is a pretty big difference (up to 20 frames, as seen here Same thing with a desktop 970 vs a 970m (15-30 frame difference, as seen here with a 970m offering roughly between a desktop 950/960 performance. Maybe I should've made myself clearer. I wasn't referring to the whole GPU family of Maxwell desktop vs Maxwell mobile, but more of each direct card. The mobile Pascals will offer the same performance as their desktop counterparts (1070 in a laptop vs a 1070 in a desktop, a 1080 in a laptop vs a 1080 in a desktop, etc). The mobile Maxwell, on the other hand, while powered by the same chip, was vastly different. A 960m performed worse than a desktop 750ti, a 970m performed worse than a desktop 960, and a 980m performed roughly the same as a desktop 970.
Also FYI the mobile 1070 has a slightly higher core count (2048) than desktop (1920), not lower which offsets the lower frequencies. It's hard to tell which is faster from aggregated benchmarks because so many notebook 1070 implementations are flawed throttled turdbook thin n lights with hard coded firmware power limits on CPU and/or GPU, thermal throttling due to woeful cooling setups, or undersized adapters. There is simply no comparison between a razer blade's "1080" with a proper 1080 in a Clevo based machine
High end laptops and desktops have always used the same GPU dies. Voltages/frequencies and core count is all that is usually different in order to cut down the power consumption. The only different thing with pascal is nvidia's marketing dept decided to not name them differently anymore. The 970/980M difference (both cut down GM204 cores) is not that much different than desky/mobile 1070 (both cut down GP104 cores). But you still need something to tell them apart because as you say the core config and speeds are different so the internet has taken to the "1070" and "1070 Mobile" distinction. Anyway 1070 (which is around what my 980M in SLI gets) just beats the pants off 970/980M there is no way the 970 should 'win'
There is no such thing as a 1070 Mobile (not really at least). The 10 series GPU's that come in laptops are the fully fledged desktop counterparts, except that some have a slightly lower CUDA count, and slightly lower clock speed. All in all, they're the same, with no more than 2-3 frames apart.
I only use it for the benchmark comparisons to be honest
Not in this case the 1070n at reference clocks and boost beats the 970 and 980 desktop at reference clocks and boosts
Desktop graphics > Mobile graphics 95% of the time.
It's based on votes. This site should be used for ballpark guess imo, anything accurate definitely not
Site's Algorithym must be bugged since it deems the 970 the winner despite losing on specs and benchmarks
comments powered by Disqus