Since the release of NVIDIA’s first Maxwell-based Quadro last spring, M6000, many folks have been patiently waiting for a mid-range variant to arrive. Well, arrive it has.
As covered in our news post from a couple of weeks ago, NVIDIA’s Quadro M2000 is special in that it’s going to be the final Maxwell-based Quadro to be released. Going forward, we have Pascal to look forward to. As cards featuring that architecture are just getting off the ground now, I wouldn’t anticipate seeing Pascal-based Quadros released for quite some time – especially where an M2000-equivalent is concerned.
NVIDIA considers the M2000 to be a replacement for the K2200 – released in the summer of 2014 – but its performance actually puts it closer to the higher-end K5000. Since the M2000 will retail for under $500 and the K5000 debuted for $2,249 in 2012, it highlights just how powerful today’s mid-range Quadro offerings are.
Compared to the outgoing K2200, the M2000 has 20% more cores, delivers up to 1.8 TFLOPs of processing power (vs. 1.3 TF), and improves memory throughput by about 30%.
M2000’s target customers include those working with CAD or lighter 3D projects. NVIDIA notes that this latest card has what it takes to deliver great experiences in SolidWorks, Siemens NX, and PTC Creo. As with the other Maxwell-based Quadros, the M2000 fully supports NVIDIA’s Iray renderer, which is available to a number of design suites as a plugin. I took an in-depth look at Iray and its plugins in December.
To help modernize the M2000 a bit, NVIDIA has chosen to offer 4x DisplayPort connections in lieu of a combination of DP and DVI. Those who need DVI should be able to find an appropriate adapter in the box (it’s important to check before purchase).
The M2000 might sport a modest aesthetic, but it still has what it takes to drive high resolution displays, which includes up to 4x 4K/60Hz, or single 5K/60Hz. Even if you go lower than 4K, the card’s display limit remains 4 (perhaps not a big surprise given the four outputs).
|NVIDIA Quadro||Cores||Core MHz||Memory||Mem MHz||Mem Bus||TDP||Price|
|Quadro M6000 24GB||3072||988||24576MB||317GB/s||384-bit||250W||~$5,000|
As covered above, NVIDIA’s slapped a $500 SRP on its Quadro M2000, although as always, street price is expected to be lower. While the card isn’t available for purchase as of the time of writing, I wouldn’t be surprised to see the card settle in at closer to $400 not long after launch. AMD’s main competition in this area is the FirePro W4300, which came out this past winter. That card is designed for low-profile PCs and currently sells for $300.
It’s worth noting that the M2000 doesn’t require the use of a PCIe power connector, thanks to its modest TDP of 75W. Being a mid-range card, you shouldn’t expect the card to break past 60°C too often, although it’s designed to handle higher temperatures if it’s installed in a more size-restrictive chassis.
Other notable features the M2000 brings includes support for NVIDIA’s Mosaic and nView technologies, as well as the company’s NVENC video encoder and HEVC decoder – the latter of which can handle video at up to 8K resolution.
On the following pages, we’ll be putting NVIDIA’s latest Quadro through a gauntlet of real-world and synthetic tests, utilizing apps from Autodesk, Adobe, SPEC, SiSoftware, and a handful of others (including light gaming tests for good measure).
All tests are run at least twice to produce an accurate result, and if for some reason an odd result creeps up, we do a third run. In the case of this particular review, no tests had to go that route, as most of the benchmarks are very good at delivering similar results with each repeated run.
Our Windows 7 Ultimate x64 test OS has a couple of key Windows services disabled (Search, Defender, Firewall, and Update), as well as Aero. During all testing, the display is kept in 4K resolution, with two exceptions: SPECapc Maya 2012 and SPECviewperf are run with a 1080p resolution. Further, Vsync and G-SYNC are disabled through the NVIDIA Control Panel.
Our test system is as follows:
|Techgage Workstation Test System|
|Processor||Intel Core i7-5960X (8-core; 3GHz)|
|Memory||Corsair Vengeance 32GB (8x4GB; DDR3-2133 11-12-11)|
|Graphics||NVIDIA GeForce GTX TITAN X 12GB (GeForce 353.30)|
NVIDIA Quadro M6000 12GB (Quadro 352.86)
NVIDIA Quadro M2000 4GB (Quadro 362.13)
NVIDIA Quadro K5200 8GB (Quadro 353.30)
NVIDIA Quadro K5000 4GB (Quadro 353.30)
AMD FirePro W4300 4GB (FirePro 15.201)
|Storage||Kingston HyperX 3K 480GB SSD|
|Power Supply||Cooler Master Silent Pro Hybrid 1300W|
|Chassis||Cooler Master Storm Trooper|
|Cooling||Thermaltake WATER3.0 Extreme Liquid|
|Displays||Acer XB280HK 28″ 4K G-SYNC Monitor|
|Et cetera||Windows 7 Professional 64-bit|
With that all covered, it’s time to jump right into the test results. Unfortunately, I had forgotten to add the results from our Quadro M5000 testing to this review, although that card is in a much different league from the M2000. I did include results for AMD’s recently-released FirePro W4300, as it’s the closest competitor to the M2000 we have on hand.