NVIDIA GeForce GTX 760 Review: The New Enthusiast Kepler
by Ryan Smith on June 25, 2013 9:00 AM EST
A little less than a month has transpired since the launch of the GeForce GTX 770, and we’re back again with another new NVIDIA card. As is usually the case with NVIDIA video card family launches, NVIDIA has started at the top and has been working their way through the list, refreshing consecutively lower-end video cards. GTX 770 saw the $400 price point refreshed with a new high-end GK104 part, and now the sub-$300 price point is due for a refresh with a new lower-end GK104 part.
Launching today, that part will be GeForce GTX 760, the direct successor to the GTX 660 Ti. Whereas the GTX 770 fully supplanted the GTX 680 and put the GTX 670 in a tough spot, GTX 760 will be doing the same thing from the other direction, replacing GTX 660 Ti while also assuming the rest of the market segment formerly inhabited by the GTX 670. As a result NVIDIA is gunning for performance between a GTX 660 Ti and GTX 670, while bringing the price down to $249, nearly $50 below GTX 660 Ti. Consequently this is a lot like the GTX 770 launch – a GK104 refresh that will see NVIDIA delivering more for less.
| GTX 770 | GTX 760 | GTX 660 Ti | GTX 560 Ti | |
| Stream Processors | 1536 | 1152 | 1344 | 384 |
| Texture Units | 128 | 96 | 112 | 64 |
| ROPs | 32 | 32 | 24 | 32 |
| Core Clock | 1046MHz | 980MHz | 915MHz | 822MHz |
| Shader Clock | N/A | N/A | N/A | 1644MHz |
| Boost Clock | 1085MHz | 1033MHz | 980MHz | N/A |
| Memory Clock | 7GHz GDDR5 | 6GHz GDDR5 | 6GHz GDDR5 | 4GHz GDDR5 |
| Memory Bus Width | 256-bit | 256-bit | 192-bit | 256-bit |
| VRAM | 2GB | 2GB | 2GB | 1GB |
| FP64 | 1/24 FP32 | 1/24 FP32 | 1/24 FP32 | 1/12 FP32 |
| TDP | 230W | 170W | 150W | 170W |
| Transistor Count | 3.5B | 3.5B | 3.5B | 1.95B |
| Manufacturing Process | TSMC 28nm | TSMC 28nm | TSMC 28nm | TSMC 40nm |
| Launch Price | $399 | $249 | $299 | $249 |
The GTX 760 is essentially composed of the only GK104 configuration we didn’t see with the 600 series: 6 SMXes attached to a full 32 ROP, 256-bit memory bus. This is the fewest number of enabled SMXes on any desktop GK104 part – GTX 670 and GTX 660 Ti both had 7 SMXes – but it’s 32 ROPs versus the 24 ROPs on GTX 660 Ti. As a result we’re looking at a configuration that technically has less shading and texturing throughput than the retiring GTX 660 Ti, but more ROP throughput and memory bandwidth than that same part, on-par with the equally retiring GTX 670.
Note that this is also the only desktop GK104 part that potentially ships with 3 GPCs; with 2 SMXes disabled, a GPC goes with it if those SMXes are part of the same GPC. Though as with the other NVIDIA parts where there’s a variable number of GPCs, we haven’t seen a measurable impact on performance, so it’s more of a technicality than a meaningful difference.
Like the GTX 770, the GTX 760 is fairly highly clocked for a GK104 part. Its base clockspeed of 980MHz is 65MHz (7%) higher than both the GTX 670 and GTX 660 Ti, which helps to offset the lost SMX. At the same time this gives the GTX 760 more ROP throughput than even the GTX 670. The end result is a product whose performance bounces between the GTX 660 Ti and GTX 670 depending on the workload, and typically is biased towards the GTX 670. Altogether we’re looking at about 92% of the GTX 660 Ti’s shading/texturing performance and 43% more ROP throughput. Memory clocks on the other hand are unchanged at 6GHz, but thanks to its full 256-bit memory bus GTX 760 will have 33% more memory bandwidth than GTX 660 Ti.
On the performance front GTX 760’s other trick compared to the GTX 600 series parts it replaces is that like the GTX 770 it’s a GPU Boost 2.0 part, meaning its boost performance is further min-maxed than GPU Boost 1.0 parts. Thermals willing, our sample boosts to 1149MHz out of the box – the official boost clock is over 100MHz lower at 1033MHz – a bigger and more frequent boosting outcome than what we saw with the GTX 660 Ti. So even though GTX 760 still theoretically has lower shader performance than GTX 660 Ti, there’s only a single benchmark where the GTX 760 doesn’t beat its predecessor, and it’s a non-gaming benchmark at that.
Meanwhile GTX 760’s TDP will stand at 170W, the same TDP as the GTX 670. Accounting for throttling differences from GPU Boost 2.0 that will have GTX 760 reaching its TDP more often, GTX 760 will essentially draw as much or more power than GTX 670, never mind GTX 660 Ti. Like GTX 770 NVIDIA has little choice but to raise their TDP here at any given tier in order to unlock more performance. 170W in turn is a rather intentional number that will allow NVIDIA’s partners to recycle their GTX 670 designs since the maximum power draw (and maximum heat generation) remain unchanged. Idle power on the other hand is going to be marginally lower, as like the GTX 770 the GTX 760 implements a lower idle clock state that shaves off a couple of watts.
Moving on, with this launch we’ll see NVIDIA shrink their desktop product stack a bit. With GK110 based cards at the high-end of NVIDIA’s stack and price compression below $500 pushing prices down, the desktop GK104 product stack is being reduced from 3 cards – GTX 660 Ti, GTX 670, GTX 680 – to just two cards. NVIDIA’s configurations leave them an out should they ever need it, but as it stands these will be the only two GK104 cards in NVIDIA’s 700 series lineup, with GTX 770 and GTX 760 splitting up the old market segments.
With a launch price of $249, GTX 760 is another aggressive launch for NVIDIA compared to both their previous generation products and AMD’s current lineup, with NVIDIA now offering performance notably better than what have been more expensive products. Other than its lower 150W TDP, GTX 660 Ti is fully redundant at this point; GTX 760 is faster and cheaper. GTX 670 is still going to be a hair faster, but with GTX 670 prices still above $300 it’s not being placed at a value sweet-spot, and like the rest of the GK104 based 600 series lineup is slowly being phased out entirely.
The more dynamic matchup will be GTX 760 versus AMD’s product lineup. $249 cuts right down the middle of AMD’s current product lineup, putting GTX 760 between the Radeon HD 7870 and 7950. At the same time NVIDIA’s goal here is to beat the 7950 in performance – keep in mind the GTX 660 Ti tied the original (non-boost) 7950 – which is something the GTX 760 doesn’t have too much trouble with. AMD and their partners have already prepared for this somewhat, as after-rebate prices on 7950 cards have come down from about $300 to about $280 in the last month, but that means GTX 760 still carries a $30 lower price tag. Once more there are no bundles in play on the NVIDIA side, so the wildcard on the AMD side will once more be their 4 game Level Up with Never Settle Reloaded bundle.
Finally, this is another hard launch. GTX 760 cards will be available from the usual retailers and e-tailers. Meanwhile since GTX 760 is designed to be a drop in replacement for GTX 670 on board designs, NVIDIA’s partners will be launching with fully custom cards right away, most of them based on their previous customized GTX 670 designs. Reference style cards will likely be few in number, but unlike the GTX 770 launch (with its relatively expensive Titan cooler) the GTX 670/760 reference cooler does not price itself out of the market.
| June 2013 GPU Pricing Comparison | |||||
| AMD | Price | NVIDIA | |||
| $400 | GeForce GTX 770 | ||||
| Radeon HD 7970 | $360 | ||||
| $350 | GeForce GTX 670 | ||||
| Radeon HD 7950 | $280 | GeForce GTX 660 Ti | |||
| $250 | GeForce GTX 760 | ||||
| Radeon HD 7870 | $200 | GeForce GTX 660 | |||
Facebook
Twitter
RSS
110 Comments
View All Comments
Nfarce - Tuesday, June 25, 2013 - link
Last year I was debating going 570 SLI and buying a second one, or selling it and going for a single 680. I went with the latter and am glad. I spent a lot of research on the decision, and 570 SLI is slightly lower than a single 680, within 90-95% depending on game. So if the 770 beats the 680 by a solid 5-10% (again, depending on games), it's going to really beat 570 SLI.Kutark - Wednesday, June 26, 2013 - link
Yeah. Im thinking i might stick with a single card. Maybe i should hold off and wait for the 760 Ti that will inevitably come. Really the GTX570 is a great card, its just getting a little long in the tooth, and frankly im kind of spoiled, I always want to make sure any game i can play runs at max settings as far as shadows/textures, etc. I'm apparently the only person on the planet who hates AA (makes things fuzzy), so i typically play most games at 1920x1080 with all settings maxed, 0xAA and 8xAnisotropic. The 570 is doing fine in that respect on everything i play now, i'm just worried about some of the upcoming games like BF4, Witcher 3, etc.I usually prefer to stay with single cards, i've just seen way too many situations where SLI didnt work (i.e. game didnt support it), produced poor results, etc. Not to mention the heat, and power consumption issues.
Regardless, thanks guys for your responses, really helped me clarify the issue.
Off Topic, im currently running an i7-2600k @ 4.1ghz stable, do you think im fine as far as CPU goes for these future games? Haswell doesn't seem to be a huge jump over Gen3 i7.
mapesdhs - Wednesday, June 26, 2013 - link
Kutark writes:
> Yeah. Im thinking i might stick with a single card. ...
Nfarce is spot on about 570 SLI, though 580 SLI can definitely beat a 680
(1.5GB 580s are quite cheap on eBay these days, eg. I've seen them go for
as little as 190 UKP total for two). Assuming you're familiar with the
difference between a 570 and 580 performance-wise, then with respect to
Firestrike Extreme, see the lower graph on this page:
http://www.legitreviews.com/article/2201/9/
and compare to the following 580 SLI results I obtained (check the
Graphics scores; the overall scores are skewed against me a bit as my
system is just a quad-core, though in this case I end up with better
overall scores anyway vs. a 680, even with the 580s @ stock):
Stock: http://www.3dmark.com/fs/588100
Oc'd: http://www.3dmark.com/fs/518352
For reference, here's just one 580 at stock, showing that it's Graphics
score matches the article's 580 quite nicely:
http://www.3dmark.com/fs/588046
Also, my oc'd 580 SLI Graphics score matches a 780. :D (4506 vs. 4483)
However, as many would rightly point out, the 780 has a huge VRAM advantage
which is ideal for games like heavily modded Skyrim (though of course there
are 3GB 580s, but they tend to cost more - mine was 170 UKP total whereas
1.5GB 580s normally go for around 100 to 125 UKP), and further differences
mean a 780 would likely be quicker in other cases, especially if you wanted
to run a multi-screen setups with AA, etc.
I haven't bothered running normal Firestrike until now, so here are stock
and oc'd runs for comparing to the upper graph on the legit page:
Stock: http://www.3dmark.com/fs/588907
Oc'd: http://www.3dmark.com/fs/588883
At stock, 580 SLI easily beats a 680. Oc'd, the Graphics score is well
ahead of a 780 (infact it's higher than the Titan). This suggests, as one
might expect, that as the visual load becomes more complicated, a single
better card like a 780 will shows its strengths, ie. SLI'd 570/580s are
good at typical HD res, but at resolutions like 2560x1440 a newer card
would be more sensible.
There's also the issue of power consumption if you added a 2nd 570; in
the long term, would the additional electricity cost end up being not that
much less than the cost difference compared to just upgrading to a single
newer card? Hard to answer this as elec prices vary wildly by location.
There's also the extra heat, and as you say the issue of which games run
well in SLI since not all do.
Btw, here's an oddity: changing the SLI rendering mode can have a
dramatic effect on Firestrike Extreme scores, eg. while still at stock
speed, here are my two 580s using Alternate Frame Rendering 1 (AFR1),
compared to the earlier link which uses NVIDIA Recommended (examine the
individual test results):
http://www.3dmark.com/compare/fs/588100/fs/588603
Graphics Test 1 doesn't change, but Graphics Test 2 increases by some
36%, hence the Graphics score shoots up 20% from 3625 to 4363. On the
other hand, the Combined Test drops by about 10%. I notice this test uses
a lot of VRAM, so perhaps AFR1 doesn't handle heavy VRAM loading so well.
I checked by running normal Firestrike with the two different SLI modes,
the result was identical, suggesting that AFR1 may be better if a game is
taxing VRAM resources a lot, ie. it may be worth manually experimenting
with one's games to see if a different SLI mode gives higher performance.
I tested with 3 cards aswell; the variation in results depending on SLI
mode is even more pronounced (not checked with 4 cards yet, need to move
them into the 3930K case). For the sake of completeness, here's the link
(done with rather low 825 core clocks as the M4E mbd used has no spare
slots to permit decent oc'ing with 3 cards):
http://www.3dmark.com/fs/518524
> ... Maybe i should hold
> off and wait for the 760 Ti that will inevitably come. ...
I read a piece yesterday which suggested NVIDIA wasn't going to release
any more cards this year, but who knows, that could easily change. It
would certainly be unusual if they didn't come out with a 760 Ti at some
point, or something equivalent.
> im kind of spoiled, I always want to make sure any game i can play runs
> at max settings as far as shadows/textures, etc. ...
:D:D Me too.
> ... I'm apparently the only
> person on the planet who hates AA (makes things fuzzy), ...
That can certainly happen with some games. Best to experiment with the
various options. Back when I was playing Oblivion on a 22" CRT at
2048x1536, I indeed found it better to leave AA off (because the dot
pitch was so small, no AA at the high res looked quite good). However,
with the games I'm playing now (FC2, Crysis2), turning on AA does look
better, but yes some modes are better than others.
> ... The 570 is doing fine in that respect on everything i play now, i'm
> just worried about some of the upcoming games like BF4, Witcher 3, etc.
If you don't plan on upgrading your display to a higher res, then adding
a 2nd 570 would work quite well performance-wise, but on the other hand...
> situations where SLI didnt work (i.e. game didnt support it), produced
> poor results, etc. Not to mention the heat, and power consumption issues.
... those are all very valid points to consider. Mind you, your CPU is
running at quite a low clock, so extra heat shouldn't affect your CPU config,
unless you have a very simple cooler.
> Off Topic, im currently running an i7-2600k @ 4.1ghz stable, do you think
> im fine as far as CPU
A 2600K will easily run at 4.5 to 4.8 depending on the chip, and many will
run at 5.0+, so you have plenty of scope for boosting your CPU performance
should you feel that necessary. The limitation on how high it can go is more
likely to be determined by your PSU, mbd, RAM, CPU cooler config and of course
just general luck of the draw re the particular 2600K you have.
Ian.
Artas1984 - Sunday, August 16, 2015 - link
You have done your research very wrong.I had GTX570 and GTX670 in the past. The performance gap was a consecutive 33 % in favor of GTX670 in 20 different games. Documented that in the forums.
Meaning GTX680 is 50 % faster than GTX570.
So SLI GTX570, if scaling is from 50 to 100 %, should be always ahead of GTX680.
skgiven - Sunday, August 4, 2013 - link
Comparing against last years reference GTX660Ti (915MHz) has little merit - most (>90%) of 660Ti's are non-reference and boosting to 1200MHz is fairly standard (22% more than 980MHz)! The most recent 660Ti's are even sweeter on the power.Including a recent FOC 660Ti and some lesser cards in SLi (GTX 650 ti Boost, which wins hands down and 460) would have made for a very nice review.
The 760 wins in high bandwidth games, but not low memory dependent games and apps, and not in terms of Performance/Watt.
BTW. I'm not seeing the price comparison, even now the GTX660Ti is still much less expensive.
AlucardX - Tuesday, June 25, 2013 - link
doesn't look like much of an improvement compared to my overclocked 7850 that i bought for $250 over a year ago..Parablooper - Wednesday, June 26, 2013 - link
Wow. On 1080p Battlefield it beats a 7970... $270 price point vs. $400.... I like AMD but they better make a move soon or they're off the market.king-dubs - Wednesday, June 26, 2013 - link
It doesn't. Anandtech is still using 7950/7970/7970GHz results from pre-12.11 drivers.http://tpucdn.com/reviews/NVIDIA/GeForce_GTX_760/i...
Also the 7970 dropped briefly to ~$300 two days ago, and the 7950 (Sapphire Dual-X) is still at $259 after MIR @ Newegg.
king-dubs - Wednesday, June 26, 2013 - link
Guru3D results are consistent with TPU:http://www.guru3d.com/index.php?ct=articles&ac...
Ryan Smith - Wednesday, June 26, 2013 - link
The 7970 results are with Catalyst 13.5 B2 (freshly composed for the GTX 780/770 reviews).The 7950 results are with Catalyst 13.6 B2 (freshly composed for this article)