Today at GTC NVIDIA announced their next GTX Titan family card. Dubbed the GTX Titan Z (no idea yet on why it’s Z), the card is NVIDIA's obligatory entry into the dual-GPU/single-card market, finally bringing NVIDIA’s flagship GK110 GPU into a dual-GPU desktop/workstation product.

While NVIDIA has not released the complete details about the product – in particular we don’t know precise clockspeeds or TDPs – we have been given some information on core configuration, memory, pricing, and availability.

  GTX Titan Z GTX Titan Black GTX 780 Ti GTX Titan
Stream Processors 2 x 2880 2880 2880 2688
Texture Units 2 x 240 240 240 224
ROPs 2 x 48 48 48 48
Core Clock 700MHz? 889MHz 875MHz 837MHz
Boost Clock ? 980MHz 928MHz 876MHz
Memory Clock 7GHz GDDR5 7GHz GDDR5 7GHz GDDR5 6GHz GDDR5
Memory Bus Width 2 x 384-bit 384-bit 384-bit 384-bit
VRAM 2 x 6GB 6GB 3GB 6GB
FP64 1/3 FP32 1/3 FP32 1/24 FP32 1/3 FP32
TDP ? 250W 250W 250W
Transistor Count 2 x 7.1B 7.1B 7.1B 7.1B
Manufacturing Process TSMC 28nm TSMC 28nm TSMC 28nm TSMC 28nm
Launch Date 04/XX/14 02/18/14 11/07/13 02/21/13
Launch Price $2999 $999 $699 $999

In brief, the GTX Titan Z is a pair of fully enabled GK110 GPUs. NVIDIA isn’t cutting any SMXes or ROP partitions to bring down power consumption, so each half of the card is equivalent to a GTX 780 Ti or GTX Titan Black, operating at whatever (presumably lower) clockspeeds NVIDIA has picked. And although we don’t have precise clockspeeds, NVIDIA has quoted the card as having 8 TFLOPS of FP32 performance, which would put the GPU clockspeed at around 700MHz, nearly 200MHz below GTX Titan Black’s base clock (to say nothing of boost clocks).

On the memory front GTX Titan Z is configured with 12GB of VRAM, 6GB per GPU. NVIDIA’s consumer arm has also released the memory clockspeed specifications, telling us that the card won’t be making any compromises there, operating at the same 7GHz memory clockspeed of the GTX Titan Black. This being something of a big accomplishment given the minimal routing space a dual-GPU card provides.

In terms of build the GTX Titan Z shares a lot of similarities to NVIDIA’s previous generation dual-GPU card, the GTX 690. NVIDIA is keeping the split blower design, with a single axial fan pushing out air via both the front and the back of the card, essentially exhausting half the hot air and sending the other half back into the case. We haven’t had any hands-on time with the card, but NVIDIA is clearly staying with the black metal styling of the GTX Titan Black.

The other major unknown right now is power consumption. GTX Titan Black is rated for 250W, and meanwhile NVIDIA was able to get a pair of roughly 200W GTX 680s into the 300W GTX 690 (with reduced clockspeeds). So it’s not implausible that GTX Titan Z is a 375W card, but we’ll have to wait and see.

But perhaps the biggest shock will be price. The GTX Titan series has already straddled the prosumer line with its $1000/GPU pricing; GTX Titan was by far the fastest thing on the gaming market in the winter of 2013, while GTX Titan Black is a bit more professional-leaning due to the existence of the GTX 780 Ti. With GTX Titan Z, NVIDIA will be asking for a cool $3000 for the card, or three-times the price of a GTX Titan Black.

It goes without saying then that GTX Titan Z is aimed at an even more limited audience than the GTX Titan and GTX Titan Black. To be sure, NVIDIA is still targeting both gamers and compute users with this card, and since it is a GeForce card it will use the standard GeForce driver stack, but the $3000 price tag is much more within the realm of compute users than gamers. For gamers this may as well be a specialty card, like an Asus ARES.

Now for compute users this will still be an expensive card, but potentially very captivating. Per FLOP GTX Titan Black is still a better deal, but with compute users there is a far greater emphasis on density. Meanwhile the GTX Titan brand has by all accounts been a success for NVIDIA, selling more cards to compute users than they had ever expected, so a product like GTX Titan Z is more directly targeted at those users. I have no doubt that there are compute users who will be happy with it – like the original GTX Titan it’s far cheaper per FP64 FLOP than any Tesla card, maintaining its “budget compute” status – but I do wonder if part of the $3000 pricing is in reaction to GTX Titan undercutting Tesla sales.

Anyhow, we should have more details next month. NVIDIA tells us that they’re expecting to launch the card in April, so we would expect to hear more about it in the next few weeks.

Source: NVIDIA

Comments Locked

64 Comments

View All Comments

  • Smartgent - Friday, April 4, 2014 - link

    In response- I have 2 R9 290's XFX DD editions in my computer, I could easily run 3-6 monitors if I choose too. My Motherboard is an Asus Sabertooth x79 running a I7 3820 with 32GB of ram. 2 SSD'd and a 2 Hard drives. It is fast!! it is the Grand National GTX of the computer world. I have never bought the $1000.00 CPU's or the $1200 GPU cards. I have had my entire system watercooled and practically silent.

    That card is not like an Lamborghini at all, because unless it is water cooled you will NEVER be able to run 2 of them in one system, there will be way too much heat exhausted into the case. 500 Watts is a ton of heat. I know, I fight thermal load all the time in my system that can generate 800 watts, on air cooling.

    My system scores in the top 95 -99% of all benchmarks out there. I can run BF4 in ultra at 130- 160 FPS on a 1080p monitor. It is smooth as class on Mantle. on one card, I average 90-120, plus I only paid $900 for the two cards. That Card is not going to beat my two cards, I can assure you that.

    In the end it is nothing but marketing to get a premium markup for an Item that isn't worth it, just like a Mercedes, but I would NEVER call it a Lamborghini, because it would have to be FAST!!
  • Smartgent - Friday, April 4, 2014 - link

    Besides, why would I spend that kind of money on one cards, when I could have 4 and blow it away. The Lamborghini analogy would only hold true, if we could only put one card in our systems.

    They need to release Maxwell and quit screwing around "milking the market"
  • Mizudori - Monday, March 31, 2014 - link

    I think I'll hold out for the Titan Z Black Edition...
  • jbrandt5 - Tuesday, April 1, 2014 - link

    Why do many make accusations of greed? Do you not know that the higher the production the cheaper the price can be? Find an old metal man and ask him to fab you a fender for your car.
    If it can be done for 3000 bucks I doubt it, but they mass produce them for 200. Before you scream greed let me know if you will work a couple hours off the clock pro bono first.
  • iAPX - Wednesday, April 2, 2014 - link

    $3000?!? This is a joke???
  • TruBlu - Friday, April 4, 2014 - link

    We shouldn't be surprised by the price. Two blacks with all cores enabled + 12gb of vram on one pcb.
  • ThatHKDude - Saturday, April 5, 2014 - link

    You guys heard about the new R9 295 X2 that's coming out on April 8th? Damn I'd love to see how these two cards compare... Though I know for sure that the AMD one will most certainly be a hell of a lot cheaper than this card.
  • Diminias - Monday, April 7, 2014 - link

    I understand that density costs money. But I don't see this card as being a huge draw. If you have enough cash to drop on this card you might as well go out and buy yourself an X79 board with more PCIe slots on it. In the end you could buy Titan Blacks for less and get more out of them due to the underclocking on the Titan Z. I think there are more economical ways to achieve this level of performance. This is simply Nvidia catering to the highend market or the window shoppers. Its impressive, but out of my price range.
  • klepp0906 - Monday, April 28, 2014 - link

    Well since my original post is (apparently spam?) I can only venture that you guys have an agreement with nvidia to avoid negative press?

    I won't re type it or anything close. Already got all the effort out of me I'm willing to denote to it.

    With that said - this will fall on it's face.

    To those who are un informed. In any OS newer than 7 SLI does not work in surround. It hasn't since I've owned my FOUR titans. I've saved months of dialogue between myself and nvidia - until they started ignoring the problem.

    Spending 10k on a PC for 25fps in ffxiv and wildstar (you read that right) while soloing, is a travesty.

    Hugely disappointed in myself for caving to fanboyism. This PC was supposed to tide me over for years. So far it has for a year, with similar performance to 1 gtx480 id imagine.

    Before trying to ride further on your name, how about you guys release proper software for the cards already on the market? While your at it hire some new mods - csr on your site is miserable and that's in comparison to operations a fraction of your size. Being ignored by several staff for over a month now?

    I've offered logs, screenshots, video, my suggestions and others with the same issues. Yet kicking out new hardware seems to trump it by a mile.

    Fwiw I'm still trying to sell the 4 titans and go amd for the first time. The fact I can't sell them is testament enough.
  • JohnnyMcCaffery - Thursday, May 1, 2014 - link

    Know offence to Nvidia, but would it be better and cheaper to SLI two TITAN GPU's than to buy the Titan Z!

Log in

Don't have an account? Sign up now