NVIDIA Launches GTX 960M/950M and GeForce 940M/930M/920M
by Jarred Walton on March 12, 2015 2:43 PM EST
Today NVIDIA officially launched their latest mobile GPUs, the GTX 960M and 950M; on a quieter note, the 940M, 930M, and 920M also showed up. NVIDIA launched the high-end GM204 back in September/October last year and brought out the mobile GTX 970M and 980M using the chips, and they more recently launched the desktop GTX 960 using a new GM206 part with up to 1024 CUDA cores. Considering the GTX 965M has 1024 CUDA cores many felt it would use GM206 as well, but that didn’t happen; in a similar fashion, those expecting (hoping) GTX 960M and 950M would use a derivative of GM206 are also going to be disappointed and it continues to use the GM107 chip.
The new GeForce GTX 960M and 950M end up being clock speed bumps from the existing GTX 860M/850M, though this time the 960M is purely Maxwell based and there’s no Kepler alternative. The GTX 950M has 640 CUDA cores running at 914MHz (+ Boost), and it can be paired with either DDR3-2000 (yuck!) or GDDR5-5000, both using a 128-bit interface. While the additional bandwidth of GDDR5 may not matter too much at lower resolutions, we’ve seen in the past that it can have a significant impact on performance at 1080p and medium or higher settings.
Interestingly, the clocks and core configurations mean that potentially the GTX 950M is actually a bit slower than GTX 850M (640 cores at 936MHz + Boost compared to 914MHz + Boost), but NVIDIA doesn't disclose the full range of base clocks and Boost clocks so the 950M will hit higher clocks on average compared to 850M. 960M meanwhile represents a minor bump in clock speeds over GTX 860M, going from 1029MHz + Boost to 1096MHz + Boost; the RAM stays the same with GDDR5-5000 providing 80GB/s of bandwidth. Keep in mind that both the 850M and 860M are marketed with "up to xxx MHz" language where NVIDIA has now switched to advertising the base clock (no "up to"). Even so, the newer parts are likely only 10% (give or take) faster than the previous generation parts.
NVIDIA’s product pages for the three lower tier GPUs reveal precious little in the way of specifications; all we know is that the parts are DirectX 12 capable and that the 920M is rated as being ~3X the performance of Intel’s HD 4400 while the 930M and 940M are 3.5X and 4X the performance rating of the HD 4400. The 940M and 930M are derived from GM108 and will replace the existing 840M/830M, while the 920M is a Kepler design that replaces the existing 820M. While NVIDIA’s specifications rate the 840M at 5.0X the performance of the HD 4400 where the 940M is "only" 4.0X the performance of HD 4400, NVIDIA changes the games used for the performance score calculations each generation so they're not directly comparable; the newer parts however are all designed to be faster than the existing parts.
Here are the full specifications for the old and new GM107 based parts, the GeForce GTX 960M/950M and the 860M/850M:
| NVIDIA GeForce GTX 960M/950M Specifications | ||||||
| GTX 960M | GTX 950M (GDDR5) |
GTX 950M (DDR3) |
GTX 860M (Maxwell) |
GTX 860M (Kepler) |
GTX 850M (GDDR5) |
|
| Processor | GM107 | GM107 | GM107 | GM107 | GK104 | GM107 |
| CUDA Cores | 640 | 640 | 640 | 640 | 1152 | 640 |
| GPU Clock (MHz) | 1096 + Boost | 914 + Boost | 914 + Boost | Up to 1029 + Boost | Up to 797 + Boost | Up to 936 + Boost |
| GDDR5 Clock | 5GHz | 5GHz | 2GHz | 5GHz | 5GHz | 5GHz |
| Memory Interface | 128-bit | 128-bit | 128-bit | 128-bit | 128-bit | 128-bit |
| Maximum Bandwidth | 80GB/s | 80GB/s | 32GB/s | 80GB/s | 80GB/s | 80GB/s |
| Maximum Memory | 4GB | 4GB | 4GB | 4GB | 4GB | 4GB |
| eDP 1.2 | Up to 3840x2160 | |||||
| LVDS | Up to 1920x1200 | |||||
| VGA | Up to 2048x1536 | |||||
| DisplayPort Multimode | Up to 3840x2160 | |||||
Along with the new parts, NVIDIA and their partners have announced several new laptops using the “new” GPUs. Below are images of the new Acer Nitro V, Alienware 13, ASUS G501, HP Omen, and Lenovo Y50. Obviously there won’t be a major difference in performance between the new GTX 900M parts and the existing GTX 800M parts, so this is most likely just NVIDIA aligning the product names for use with the upcoming Broadwell systems.
Source: NVIDIA
Facebook
Twitter
RSS
31 Comments
View All Comments
JarredWalton - Monday, March 16, 2015 - link
I think the AMD GPUs are probably less efficient overall, but who knows? My guess would be a 940M, or maybe Apple will do a custom order from NVIDIA where they get a 128-bit memory bus with something like 512 cores. Really, I still don't get why NVIDIA isn't doing any GM206 mobile parts yet -- do one of those with lower clocks and maybe disable a couple SMX as well, and it could be a very interesting part. Maybe Apple will do a custom order to get what they want for the next rMPB...or maybe Apple will just use Broadwell GT4e and have no dGPU?SPBHM - Thursday, March 12, 2015 - link
I hate how they have 2 very different performing models under the same name, one 950M with 80GB/s memory and other with 32GB/s, and most consumers can't tell what version they are buying, the DDR3 model should be called 950M Le, 940M or something else.Hrel - Thursday, March 12, 2015 - link
Yeah, they've been doing this for too long. It's as infuriating as ever. Makes me happy when I can justify not buying Nvidia, which I can't do at all in laptops, but in Desktop my hatred for Nvidia's business practices makes me not buy them. It's just a bonus when AMD offers a better bang/buck, which they have quite consistently.Wish AMD could come up with legitimate competition in mobile however, they need their version of Optimus to meet performance and stability parity with Optimus.
Dark_Archonis - Thursday, March 12, 2015 - link
Yes I can't stand that either. I wish it was illegal for technology to be sold under the exact same model name, yet vastly different internal configurations.I still buy Nvidia, because I absolutely can't stand AMD, and there are no other viable alternatives. That's why I usually stick to the mid-high-end Nvidia offerings that don't pull any of this shady nonsense with one model name having two vastly different RAM configurations and speeds.
MrSpadge - Thursday, March 12, 2015 - link
I agree in some way - seeing those mobile specs pretty much always makes me want to puke. It's so clearly aimed at "but it's got the bigger numbers" customers, it makes me sad that they get away from it. And even more so that the OEMs are probably demanding it like this.Anyway, my conclusion is the opposite of yours: nVidia for the desktop (to run GPU-Grid and other GP-GPU software 24/7 energy efficiently), but not mobile. I wouldn't want an AMD there either, though.
JarredWalton - Thursday, March 12, 2015 - link
Truth is, NVIDIA only makes the DDR3 GTX 950M for one reason: there's at least one major notebook OEM that wants to save a few pennies. I'll refrain from pointing out the culprit, but I'm sure others can do so.jeffry - Friday, March 13, 2015 - link
I agree on that one. With older Desktop GPUs, the names designated are even worse in some cases (eg GT-630 / GT-640, check them at the nvidia homepage and take a look at the specifications)Aikouka - Thursday, March 12, 2015 - link
Is the 960M the exact same as the 860M, or does it have some of the hardware changes that the desktop 960 has (i.e. PureVideo that supports h.265)?MrSpadge - Thursday, March 12, 2015 - link
It's the same chip, so no changes apart from a handful of MHz more.jeffkibuule - Thursday, March 12, 2015 - link
How do these compare to the 750M in the MacBook Pro (which feels like only a small bump compared to the 650M from *gasp* 2012!). Am I going to have to wait another year for a *real* upgrade from 3 year old tech? Where are the 20nm or 14/16nm FinFET GPUs? Why does mobile always get the shaft? =/