Positioning & Architecture
The GeForce RTX 5060 Ti 16 GB is NVIDIA's fifth graphics card launch this year, and the Blackwell gaming stack is almost complete. Today NVIDIA also launches the RTX 5060 Ti 8 GB, but nobody was able to provide any review samples—everyone's focusing on the 16 GB model. Later in May, probably around Computex time, the RTX 5060 non-Ti will be launched, which comes as an 8 GB model only.

Unlike other launches, NVIDIA has allowed all reviews to go live today, both MSRP and non-MSRP. We have for you: ASUS RTX 5060 Ti Prime 16 GB, ASUS RTX 5060 Ti TUF 16 GB, MSI RTX 5060 Ti Gaming 16 GB, MSI RTX 5060 Ti Gaming Trio 16 GB, Palit RTX 5060 Ti Infinity 3 16 GB and Zotac RTX 5060 Ti AMP 16 GB.

With the RTX 5060 Series, NVIDIA is introducing the GB206 graphics processor to their lineup. It comes with 4,608 cores, which are all enabled in the RTX 5060 Ti. Compared to the RTX 4060 Ti, that's an increase of 6%. You also get 48 ROPs, 36 RT cores and a 128-bit GDDR6 memory interface. As mentioned before, the RTX 5060 Ti comes in both 8 GB and 16 GB variants. All our reviews today cover the 16 GB models, but we'll buy an 8 GB card as soon as possible, to be able to tell you what to expect.

The Blackwell architecture introduces several architectural improvements under the hood, like giving all shaders the ability to run FP32 or INT32 instructions, on Ada only half the cores had that ability. The Tensor Cores are now accessible from the shaders through a new Microsoft DirectX API, and they now support FP4 and INT4 instructions which run at lower precision, but much faster with less memory usage. There's numerous additional architecture improvements, we talked about all of them on the first pages of this review.

From a fabrication perspective nothing has changed though—Blackwell is built on the same 5 nanometer "NVIDIA 4N" TSMC node as last generation's Ada. NVIDIA claims this is a "4 nanometer process," but during Ada it was confirmed that NVIDIA 4N is actually not TSMC N4 (note the order of N and 4), but 5 nanometer. At the end of the day the actual number doesn't matter much, what's important is that NVIDIA is using the same process node.

Performance
For this launch we've updated our test setup again and retested all comparison cards with the newest drivers. We also updated the BIOS on our 9800X3D and added several new games, like our first RT exclusive title Indiana Jones, and Path Tracing is now an additional section in all reviews. At 1440p, with pure rasterization, without ray tracing or DLSS, we measured a 13% performance uplift over the RTX 4060 Ti 16 GB, which is quite small. At 4K, the increase is bigger, reaching 20%. A gen-over-gen improvement of 13% is not much, but at least it's more than RTX 5080 which only got 8% at 1440p. The RTX 5090, 5070 Ti and RTX 5070 did better, giving you an extra 20% at 1440p. Compared to the RTX 3060 Ti from two generations ago, the performance uplift is only 31%, usually we expect a doubling in performance over two generations. With these numbers the RTX 5060 Ti ends up a bit faster than AMD's aging Radeon RX 7700 XT, 11% behind the RX 7800 XT, which is much more expensive of course. NVIDIA's RTX 5070 non-Ti is a whopping 39% faster. The RTX 5060 Ti does not catch last generation's RTX 4070 either, which remains 16% ahead. If you've seen our manual overclocking results, there is a ton of headroom, like +15%, so I have no idea why NVIDIA clocked their card so low, especially considering the fact that it's underperforming by so much.

The RTX 5060 Ti is a fantastic choice for gaming at 1080p Full HD, especially with a high-refresh-rate monitor. It also has enough muscle for 1440p gaming in most games at maximum details. Some of the most demanding titles, or when RT is enabled will require you to use DLSS though to get a good gaming experience.

Thanks to its factory overclock, the ASUS TUF OC gains an extra 4% in real-life performance over the base RTX 5060 Ti, which is small, but every bit helps of course. Competing cards achieve similar performance levels, with all cards hitting +3% or +4.

Ray Tracing & Neural Rendering
Ray tracing is the future and Blackwell comes with several improvements here. Still, gen-over-gen, when compared to the RTX 4060 Ti 16 GB, the improvement is just 10%. Compared to the RTX 4060 Ti with 8 GB, the gap is bigger though, an impressive +56% (!)—because 8 GB VRAM will fail in many games at 1440p with RT enabled. Our RTX 4060 Ti 8 GB vs 16 GB results should be a decent proxy for what to expect from RTX 5060 Ti 8 GB, which is probably the reason why NV is focusing on 16 GB reviews only. While AMD hasn't released their Radeon RX 9060 Series yet, it is confirmed that they have given their new RDNA 4 architecture some extra improvements in the RT core, so they will probably be competitive in both raster and RT. With Blackwell, NVIDIA is introducing several new technologies. The most interesting one is Neural Rendering, which is exposed through a Microsoft DirectX API (Cooperative Vectors). This ensures that the feature is universally available for all GPU vendors to implement, so game developers should be highly motivated to pick it up.

VRAM
The RTX 5060 Ti comes with both 8 GB and 16 GB VRAM. We've tested the 16 GB models and with that much memory, VRAM is definitely a non-issue. Not a single game in our test suite will run into trouble with 16 GB VRAM, not with ray tracing, not with path tracing. That definitely makes 16 GB the more future-proof option, but it's also an expensive insurance policy. While 8 GB is definitely not enough for a lot of scenarios, I still think it can be a reasonable compromise if you want to save cost and are willing to dial textures down a notch, or use upscaling, which you'll probably have to use anyway. 12 GB would have been a good middle choice, as that's good enough for virtually all titles at 1080p and 1440p, but more economical. NVIDIA designed their GPU with a 128-bit memory bus, which means four memory chips, which each connect using a 32-bit interface. On the RTX 5060 Ti 16 GB, NVIDIA doubled up the memories to eight chips, so that two each share a 32-bit interface (they do not use larger capacity chips). A 192-bit bus would certainly be possible, like on RTX 5070, but that would have required a wider bus design in the GPU, with support for the extra bus width, and more pins in the design, and a more complex PCB, etc. All these changes would make the card more expensive. More memory does not automagically turn into additional performance in every single game—I'm sure we'll see some of that in our 8 GB RTX 5060 Ti review.

DLSS 4 Upscaling & Frame Generation
NVIDIA made a big marketing push to tell everyone how awesome DLSS 4 is, and they are not wrong. First of all, DLSS 4 Multi-Frame-Generation. While DLSS 3 doubled the framerates by generating a single new frame, DLSS 4 can now triple or quadruple the frame count. In our testing this worked very well and delivered the expected FPS rates. When using FG, gaming latency does NOT scale linearly with FPS, but given a base FPS of like 40 or 50, DLSS x4 works great to achieve the smoothness of over 150 FPS, with similar latency than you started out with. Image quality is good, if you know what to look for you can see some halos around the player, but that's nothing you'd notice in actual gameplay.

Just to clarify, even multi-frame-generation will not turn 15 base FPS into 60 "playable" FPS. Sure, the movements will be very smooth, just like 60, but the game would react to your inputs at a rate of 15 FPS, which is noticeably sluggish. That's why the "base" FPS value is so important, as mentioned before, 40+ works very well, but it also depends on the type of game. Some slower titles, not shooters, will run great, even with a base FPS of 30.

For the RTX 5060 Ti specifically and its relatively low overall performance, I noticed that at 1440p with RT, you'll often end up with a base FPS that's too low for an optimal frame generation experience, resulting in noticeable input lag. In some cases the input lag with x4 frame generation was too noticeable, but the x2 frame generation experience was "good enough," even though the smoothness (from extra FPS) wasn't as high. Definitely play around with the settings.

Need lower latency? Then activate DLSS 4 Upscaling, which lowers the render resolution and scales up the native frame. In the past there were a lot of debates whether DLSS upscaling image quality is good enough, some people even claimed "better than native"—I strongly disagree with that—I'm one of the people who are allergic to DLSS 3 upscaling, even at "quality." With Blackwell, NVIDIA is introducing a "Transformer" upscaling model for DLSS, which is a major improvement over the previous "CNN" model. I tested Transformer and I'm in love. The image quality is so good, "Quality" looks like native, sometimes better. There is no more flickering or low-res smeared out textures on the horizon. Thin wires are crystal clear, even at sub-4K resolution! You really have to see it for yourself to appreciate it, it's almost like magic. The best thing? DLSS Transformer is available not only on GeForce 50, but uses Tensor Cores on all GeForce RTX cards! While it comes with a roughly 10% performance hit compared to CNN, I would never go back to CNN.

Despite all the drama surrounding "fake frames," and the fact that it's not perfect, it's still impressive what DLSS can do, and I'm not saying that because NVIDIA would love to see me write this. While 1440p native at max settings with ray tracing is a stuttery mess in many games on the RTX 5060 Ti, enabling DLSS Quality and x4 frame gen turns it into a beautiful, extremely playable gaming experience, resulting in a night-and-day difference. Sure, if you look hard you can spot something that's not perfect, and if you stop playing the game and start reviewing the latency you might be able to feel something, but if you really just plan on enjoying your games it's a great alternative to spending a few hundred dollars extra on a faster GPU.

Physical Design, Heat & Noise
The ASUS TUF is the company's most premium offering for the RTX 5060 Ti lineup. The card aced all our thermal tests and performed extremely well. With just 60°C under full load, the card runs extremely cool. It's also operating very quiet, emitting just 29 dBA. Thanks to the dual BIOS, you can reduce the noise levels even further. Once the quiet BIOS is activated, the card runs at a whisper-quiet 24 dBA—inaudible when installed in any case with other actively cooled components.

Our apples-to-apples cooler comparison test, which runs the cards in a normalized way reveals that the cooler on the TUF is actually a tiny bit weaker than what's offered on the lower-tiered ASUS Prime. That's unexpected, and I'm not exactly sure what causes it, maybe the bigger cutout on the backplate, or different fans, the heatsink assembly seems very similar. Compared to other cards the TUF cooler is more powerful than any other non-ASUS card tested today.

PCI-Express 5.0
NVIDIA's GeForce Blackwell graphics cards are the first high-end consumer models to support PCI-Express 5.0. This increases the available PCIe bandwidth to the GPU, yielding a small performance benefit. Of course PCIe Gen 5 is backwards compatible with older versions, so you'll be able to run the cards in an older computer, too. The RTX 5060 Series specifically operates at PCIe 5.0 x8, not x16 like the other RTX 50 Blackwell cards. This cuts the available bandwidth in half, but the switch from Gen 4 to Gen 5 doubled it.

We still ran a full round of testing, to compare PCIe 5.0 x8 with PCIe 4.0 x8, and PCIE 3.0 x8 for people with really old systems. You can find our test results here.

Power Consumption
Power consumption of the RTX 5060 Ti is good. While some other Blackwell cards had quite high power consumption in idle, multi-monitor and media playback, this isn't a problem at all here. The extra memory chips do increase the power draw slightly, but it's not enough to worry about. In gaming, I noticed that all models reach around 160 W without ray tracing, which is well below the default power limit of 180 W. However, when ray tracing is enabled, power usage increases and occasionally reaches the power limit—still, the RTX 5060 Ti is definitely not power starved.

Overclocking
We've seen good overclocking potential from some previous Blackwell cards, but the RTX 5060 Ti is remarkable. With manual OC we were able to increase the clocks by 400 to 500 MHz, which turned into a +15% real-life improvement. That's real FPS gains, not some theoretical increase, and that's the missing performance that would have turned RTX 5060 Ti's gen-over-gen rating from "meh" to "nice." What puzzles me is that NVIDIA must know about this, they spend a significant amount of time on planning the final frequencies, hundreds of people are busy benchmarking, comparing, theory-crafting, and then they launch an essentially underclocked product. Power is not the problem here, it increases only marginally. Maybe to tempt people to buy RTX 5070? Maybe to leave room for RTX 5060 Ti Super? Maybe so they can maximize harvesting and use chips that don't clock so high due to manufacturing variances? I don't know, it's a lost opportunity, but excellent potential for people who are willing to do some manual overclocking. Memory overclocking is equally impressive and topped out at NVIDIA's artificial cap of +375 MHz / +3000 MT/s—the chips could certainly take more.

Pricing & Alternatives
NVIDIA's MSRP for the RTX 5060 Ti 16 GB is set at $430, which is not bad, but not impressive either. At that price point it's a good option, especially you want 16 GB (not 8 GB or 12 GB). It's a considerably better offering than the AMD Radeon RX 7700 XT, which sells for $450 currently, with lower performance in all cases, smaller VRAM, no DLSS, and much worse efficiency. AMD's Radeon RX 7800 XT 16 GB goes for $540, with only 14% higher raster performance, 10% lower RT performance, 100 W higher power draw and no DLSS—I'd pick the RTX 5060 Ti over that any day. So far, RTX 5060 Ti is doing well, but an interesting alternative could be RTX 4070 12 GB, if you can find it at similar pricing as RTX 5060 Ti. The 12 GB VRAM size will be sufficient for nearly all games, you do get higher overall performance in raster and ray tracing, DLSS frame generation is x2 only, but you still have DLSS Transformer upscaling, similar efficiency. On the other hand, at $600+ for the RTX 4070, I'd prefer the RTX 5060 Ti. If you can, definitely save up for the RTX 5070. While it has "only" 12 GB, its overall performance is so much better than the RTX 5060 Ti at not that much of a price increase.

Just like other recent launches, I'm quite certain that the MSRP is a fake price point that will be reached only for a very small initial volume that bots snatch up, and actual market pricing will be much higher. Based on the pricing data for custom designs it seems that the real MSRP is actually, $500, and I'm expecting that much for any RTX 5060 Ti 16 GB once the initial stock is replenished, which probably already happened. RTX 5060 Ti 8 GB should end up at around $430 (from a $375 MSRP). Sales should be live from today, so we'll know more soon.

While ASUS ignored multiple requests for pricing, now we know why, the card is listed for $600 on Newegg, which makes it $170 more expensive than the baseline MSRP, or +40%. In return, you do get a fantastic cooler with excellent fan settings that result in very little noise. You also get the bigger manual power limit adjustment range, which results in the best overclocked performance, by a very small margin. Still, that price doesn't make much sense otherwise, you should just buy a 5070 with that money.

Looking at future options, we have AMD's Radeon RX 9060 Series coming up soon, which could definitely shake things up in this segment. The big question is whether AMD's card will be faster than RTX 5060 Ti, what Team Red is doing with VRAM, and of course, whether they managed to come up with a new pricing strategy, other than "NVIDIA minus 10%." Personally, I'm very interested in my results for the RTX 5060 Ti 8 GB, which I'm trying to buy now, and of course the RTX 5060 non-Ti, which could be close, if they clock it high enough. Maybe Intel has an ace up their sleeves, their bigger Arc Battlemage cards could add more competition, but the release date is completely unknown, some rumors say that those cards have been canceled.