WEBVTT 00:00:00.000 --> 00:00:04.560 It's here, it is ripping fast, and it's $2,000 US dollars. 00:00:04.560 --> 00:00:07.800 But in exchange for your least favorite of kidneys, 00:00:07.800 --> 00:00:11.960 NVIDIA promises that their brand new GeForce RTX 5090 00:00:11.960 --> 00:00:17.480 will deliver a level of performance that obliterates their only real competition. 00:00:17.480 --> 00:00:20.560 NVIDIA, more GPU cores, boom. 00:00:20.560 --> 00:00:23.760 More VRAM, and faster VRAM, boom, boom. 00:00:23.760 --> 00:00:31.800 Enhanced RT and AI cores, wider memory bus, and PCIe Gen 5, boom, boom, boom. 00:00:31.800 --> 00:00:37.000 On top of that, NVIDIA has packed in a deep learning super shed load of new features that I would 00:00:37.000 --> 00:00:41.560 love to tell you about. But unless NVIDIA also invented AI teeth extraction, 00:00:41.560 --> 00:00:46.520 I won't be able to. So instead, I leave this review in your capable hands. 00:00:46.520 --> 00:00:47.400 See you later. 00:00:49.920 --> 00:00:52.920 I got it, I got it, I got it. First up, graphics performance. 00:00:52.920 --> 00:00:54.000 Let's cut to the chase. 00:00:56.520 --> 00:01:04.760 Let's get right to raw gaming results. 00:01:04.760 --> 00:01:08.360 No ray tracing, no upscaling, and we're starting with 1440p. 00:01:08.360 --> 00:01:13.000 Across our suite of games at 1440p, the 5090 never falls flat on its face, obviously, 00:01:13.000 --> 00:01:16.120 but still manages to be underwhelming. 00:01:16.120 --> 00:01:21.520 In the Vulcan-based Red Dead Redemption 2, we see less than a 10% improvement over the 4090, 00:01:21.520 --> 00:01:24.880 and that lackluster uplift is repeated in F124. 00:01:24.920 --> 00:01:30.960 More problematic is the embarrassingly small 30% lead over the 7900XTX, which frequently 00:01:30.960 --> 00:01:34.520 goes for a little over two-fifths of the price. 00:01:34.520 --> 00:01:40.040 Oof. And Returnal doesn't bring better news. But as we move on to newer, more graphically intensive games, 00:01:40.040 --> 00:01:44.640 the 5090 does start to pull away from the pack. In the gorgeous thriller, Alan Wake 2, 00:01:44.640 --> 00:01:52.520 it beats the 3090 Ti by more than double and looks great in Blacksmith Wukong, beating the 4090 by 27%. 00:01:52.560 --> 00:01:56.800 Cyberpunk is another strong point compared to the previous generations, but as low as they are 00:01:56.800 --> 00:02:02.240 on the chart, it's worth noting AMD's strong performance per dollar in this game, at least when ray tracing 00:02:02.240 --> 00:02:07.960 isn't enabled. We'll get to that later. For now, this might be obvious, but if you are a 1440p player, 00:02:07.960 --> 00:02:11.560 the 5090 is overkill with the current crop of CPUs. 00:02:11.560 --> 00:02:15.960 If you're on the latest 9800X3D, you might find that the 5090 exerts a little bit more 00:02:15.960 --> 00:02:19.000 of a commanding lead, but I think that anyone with this setup 00:02:19.000 --> 00:02:22.720 should be putting their money into a new monitor rather than a new CPU. 00:02:22.720 --> 00:02:27.320 Let's move on to 4K testing, where the CPU bottlenecks are less likely to rear their ugly heads. 00:02:27.320 --> 00:02:30.400 In Cyberpunk, the 5090 is the first card 00:02:30.400 --> 00:02:33.560 to ever crack triple digits at our ultra preset, 00:02:33.560 --> 00:02:37.520 scoring a 30 FPS lead over the 4090. 00:02:37.520 --> 00:02:42.440 In Alan Wake 2, the story remains largely the same, offering a noticeable difference in playability 00:02:42.440 --> 00:02:47.040 compared to any previous flagship. Blacksmith Wukong at cinematic settings, however, 00:02:47.040 --> 00:02:50.520 is the Everest-like summit, where even the 5090 00:02:50.560 --> 00:02:56.440 falls short of 60 FPS average. Perhaps an overclocking Sherpa could get us to the peak, 00:02:56.440 --> 00:03:02.000 but that's a subject for another day. In Red Dead Redemption 2, the 5090 does not impress, 00:03:02.000 --> 00:03:06.160 especially when you consider its price. And in F124, the 5090 continues to operate 00:03:06.160 --> 00:03:11.360 at that kind of level of performance that no one else can touch. The problem is that for all the hype, 00:03:11.360 --> 00:03:18.320 the performance bump is roughly on par with the price bump, making the 5090 look less like a truly next-generation product 00:03:18.360 --> 00:03:22.040 and more like a 4090 Super GT Zikaiburkei. 00:03:22.040 --> 00:03:27.360 But what's the deal? I thought that Blackwell was supposed to be the giant leap forward with all that flip metering 00:03:27.360 --> 00:03:30.800 and neural rendering and increased rate triangle intersections. 00:03:30.800 --> 00:03:34.800 What the fuck? Whoa, whoa, whoa, whoa, all right, hold on. That's a lot of words, 00:03:34.800 --> 00:03:37.920 but to understand how they're going to impact performance, 00:03:37.920 --> 00:03:41.480 and they will, we need to understand what they mean. 00:03:41.480 --> 00:03:45.360 See, Blackwell brings so many new enhancements 00:03:45.400 --> 00:03:50.000 that NVIDIA marketing doesn't even call it a GPU architecture. 00:03:50.000 --> 00:03:54.200 No, it's called a neural rendering architecture. 00:03:54.200 --> 00:03:58.240 So what is that? As far as we can tell, 00:03:58.240 --> 00:04:02.200 it's about equal parts, genuine innovation and marketing fluff. 00:04:02.200 --> 00:04:07.520 We'll start with the innovation. Up until this point, NVIDIA's AI accelerating tensor cores 00:04:07.520 --> 00:04:12.480 could not be accessed by a graphics API like Vulkan or DirectX. 00:04:12.480 --> 00:04:18.040 But through collaboration with Microsoft, DirectX now has the Cooperative Vectors API, 00:04:18.040 --> 00:04:21.440 which means that gamers can use neural shaders. 00:04:21.440 --> 00:04:26.400 Unlike typical shaders, this allows geometry to be imbued with extra properties. 00:04:26.400 --> 00:04:30.200 But now that extra property could be a small neural network 00:04:30.200 --> 00:04:34.840 that could generate more geometry or help ease ray tracing calculations. 00:04:34.840 --> 00:04:40.000 For instance, mega geometry. This one allows for real time generation 00:04:40.000 --> 00:04:44.640 of level of detail steps without requiring any normal maps. 00:04:44.640 --> 00:04:49.400 Think of like UE5's Nanite, which helps ease jarring LOD change effects 00:04:49.400 --> 00:04:52.880 and saves developer time, but with, you know, AI. 00:04:52.880 --> 00:04:57.240 To take advantage of these features, NVIDIA loaded the 5090 with the hardware it needs 00:04:57.240 --> 00:05:00.880 to accelerate them. It's got fifth gen tensor cores, 00:05:00.880 --> 00:05:07.440 which drastically reduces memory usage for simpler AI models that don't require high precision. 00:05:07.440 --> 00:05:10.960 As for the non-AI stuff, we get upgraded fourth gen RT cores, 00:05:10.960 --> 00:05:16.480 which now double the ray-triangle intersection rate with just 75% of the memory footprint. 00:05:16.480 --> 00:05:21.280 And as for the regular old CUDA cores, well, those just don't seem to have changed very much. 00:05:21.280 --> 00:05:24.640 So far, the 5090 has managed a best case scenario 00:05:24.640 --> 00:05:31.720 of about 30% faster than its predecessor, seemingly entirely thanks to the 33% higher GPU core camp. 00:05:31.720 --> 00:05:35.160 This, combined with their reuse of TSMC's 4N process node 00:05:35.160 --> 00:05:40.080 from last gen, explains why the new chip is so big and why NVIDIA had to sacrifice some clock speed 00:05:40.120 --> 00:05:44.440 to keep their yields, and therefore pricing still attainable to the 1%. 00:05:44.440 --> 00:05:49.720 GDDR7, on the other hand, is kind of a big deal. It boasts double the data rate of GDDR6 00:05:49.720 --> 00:05:54.400 while using half as much power per bit. This is an enlarged part thanks to the shift 00:05:54.400 --> 00:05:59.100 to PAM3 signaling. PAM, short for pulse amplitude modulation, 00:05:59.100 --> 00:06:02.520 is akin to how we store data in multi-level cell flash storage. 00:06:02.520 --> 00:06:05.800 GDDR6 uses PAM4, meaning that each clock 00:06:05.800 --> 00:06:09.520 can be encoded for four different states, rather than just two. 00:06:09.520 --> 00:06:15.120 But it came with a big trade-off, the error rate, since the signals are so similar in amplitude 00:06:15.120 --> 00:06:18.720 that sometimes they can be hard to tell apart, especially when there's interference. 00:06:18.720 --> 00:06:23.240 PAM3 improves the situation by just trying to handle three states instead of four, 00:06:23.240 --> 00:06:27.320 giving a little bit more room between each of them. This improves signal integrity, 00:06:27.320 --> 00:06:30.480 allowing GDDR7 to run at higher frequency 00:06:30.480 --> 00:06:37.040 while consuming less power to make up for the trade-offs. And let's not forget that we finally got 32 gigs of VRAM. 00:06:37.040 --> 00:06:42.040 This will be a huge jump for AIDarks, and maybe gamers someday. 00:06:42.040 --> 00:06:46.960 But there are some other cool things, like NVIDIA's new ninth-gen N-Vanc hardware video encoders, 00:06:46.960 --> 00:06:50.160 which support higher-quality 422 10-bit video. 00:06:50.160 --> 00:06:53.320 This, for the right people, is a huge deal, 00:06:53.320 --> 00:06:57.960 and might make Blackwell a must-have upgrade. And for the folks out there who own monitors, 00:06:57.960 --> 00:07:03.520 hi, Ploof, we finally get a card that can actually take advantage of DP 2.1 UHBR20, 00:07:03.520 --> 00:07:07.280 a new DisplayPort standard that can drive 4K 240Hz 00:07:07.280 --> 00:07:11.280 without display-stream compression. And all of this while talking to your computer 00:07:11.280 --> 00:07:16.940 at PCIe Gen 5. It's 2025, and ray-tracing is no longer an afterthought, 00:07:16.940 --> 00:07:20.680 or even a choice in some cases, with the new name of Jones being the first game 00:07:20.680 --> 00:07:24.580 to outright require support. So let's talk about it. 00:07:24.580 --> 00:07:30.000 For RT testing, we use the highest settings, starting at 1440, and I want to get this out of the way. 00:07:30.000 --> 00:07:34.200 AMD does not ray-trace well. Now, in fact, 2 makes for a very playable experience 00:07:34.200 --> 00:07:37.600 on the 5090, with 1% lows well above 60 FPS. 00:07:37.600 --> 00:07:41.580 Numbers, it can't quite hit yet on the absolutely brutal Blackmith Wukong, 00:07:41.580 --> 00:07:45.440 though it is playable, unlike the poor 7900XTX. 00:07:45.440 --> 00:07:50.800 Ouch! In Cyberpunk, the 5090 has just a 20% lead over the 4090, 00:07:50.800 --> 00:07:54.820 but compared to the 4080 Super, it maintains its price-to-performance ratio, 00:07:54.820 --> 00:07:58.480 which I generally consider to be pretty darn acceptable for a Halo-class card. 00:07:58.520 --> 00:08:03.320 In the lightly ray-traced F124, AMD comes back to life a little, 00:08:03.320 --> 00:08:07.520 performing well against the 4080 Super, and the same can be said for Returnal, 00:08:07.520 --> 00:08:12.520 but there's no question that the 5090 is king for RT at 1440P, 00:08:13.600 --> 00:08:19.160 with a crown that only gets more dazzling at 4K. Blackmith Wukong falls below what we consider playable 00:08:19.160 --> 00:08:23.000 for an intense action game. Don't worry, we'll talk about AI upscaling later, 00:08:23.000 --> 00:08:28.320 because first, dang, look at this thing! Maintaining performance in the 50s at these settings, 00:08:28.480 --> 00:08:32.160 this economy? Dang, NVIDIA, that's pretty impressive. 00:08:32.160 --> 00:08:35.300 And if you care more about absolute cinema than framerate, 00:08:35.300 --> 00:08:40.480 well, it holds above 30 FPS in Alan Wake 2, which should go great with your popcorn. 00:08:40.480 --> 00:08:44.080 F124 and Returnal are similar stories as the 1440P results, 00:08:44.080 --> 00:08:48.880 just with more pixels and fewer FPS. All of this taken together means we're looking at 00:08:48.880 --> 00:08:53.600 a greater than 30% lead over last gen at a 25% higher price, 00:08:53.600 --> 00:08:57.020 meaning the new RT cores are providing some benefit, 00:08:57.020 --> 00:09:01.420 but it's pretty small compared to the impact of NVIDIA just plunking in more of them. 00:09:01.420 --> 00:09:04.540 This is obviously a downer compared to the good old days 00:09:04.540 --> 00:09:09.140 when we used to get yearly GPU refreshes with dramatic improvements to performance per dollar. 00:09:09.140 --> 00:09:13.840 But it's clear that unless cutting-edge semiconductor manufacturing miraculously gets cheaper, 00:09:13.840 --> 00:09:18.940 those days are never coming back. So if we compare this more to, say, 00:09:18.940 --> 00:09:23.240 adding a second card in SLI, a feature NVIDIA no longer supports, 00:09:23.240 --> 00:09:29.540 then the glass half-full-take is, hey, at least it costs less than $240.90s. 00:09:29.540 --> 00:09:32.900 But NVIDIA still has some tricks up their sleeve. 00:09:32.900 --> 00:09:37.060 Holy heck, that's one tight leather jacket. How the heck did you fit that stuff in those sleeves? 00:09:37.060 --> 00:09:41.820 With DLSS4 and multi-frame gen, by making use of flip metering and swapping them 00:09:41.820 --> 00:09:46.020 from convolution neural networks to transformer-based models. 00:09:46.020 --> 00:09:49.900 There's a lot of words again, lots of words again. Let's break it down. 00:09:49.900 --> 00:09:53.980 DLSS4 is NVIDIA's latest suite of AI enhancements, 00:09:53.980 --> 00:09:58.260 and it's the biggest change in years. Previous versions of DLSS included 00:09:58.260 --> 00:10:01.460 a convolutional neural network or CNN. 00:10:01.460 --> 00:10:04.940 A CNN can be thought of as a series of filters 00:10:04.940 --> 00:10:08.740 that look for specific details. When used for image processing, 00:10:08.740 --> 00:10:15.220 one layer could be looking for vertical edges, one for horizontal edges, and one for contrast, et cetera. 00:10:15.220 --> 00:10:19.980 The neural network then observes the results from the filters and can use that information 00:10:19.980 --> 00:10:24.340 to identify things. Like if an image contains a dog or a stop sign 00:10:24.340 --> 00:10:27.340 and seems convoluted, well, it literally is. 00:10:27.340 --> 00:10:30.860 On 4,000 series GPUs, this information was combined 00:10:30.860 --> 00:10:34.780 with an optical flow accelerator that interpreted the motion in the scene 00:10:34.780 --> 00:10:38.460 to upscale or generate frames. So why the switch? 00:10:38.460 --> 00:10:41.940 Scaling. Each filter can only scan and compute 00:10:41.940 --> 00:10:46.340 a small number of pixels at a time. When you have millions of pixels, 00:10:46.340 --> 00:10:50.140 dozens of times per second, increasing performance can be tough. 00:10:50.140 --> 00:10:54.940 So DLSS uses a new transformer model, which, as NVIDIA explains, 00:10:54.940 --> 00:11:00.140 allows them to evaluate the relative importance of each pixel across an entire frame 00:11:00.140 --> 00:11:04.580 and over multiple frames to achieve a deeper understanding of the scenes 00:11:04.580 --> 00:11:08.580 that offers greater stability, reduced ghosting, higher detail in motion, 00:11:08.580 --> 00:11:11.780 and smoother edges. They also scale better, 00:11:11.780 --> 00:11:16.660 which is part of why they have become so heavily used in things like large language models. 00:11:16.660 --> 00:11:22.500 The transformer is the T in chat GPT, so while a CNN can see this picture and say, 00:11:22.500 --> 00:11:25.820 there is a cat, there is a product from LTTstore.com. 00:11:25.820 --> 00:11:31.340 A transformer might say, there is a cat enjoying the premium CRT-themed peck cave 00:11:31.340 --> 00:11:36.380 from LTTstore.com. However, while a transformer can process 00:11:36.380 --> 00:11:40.340 complete images faster, it does require more data for training, 00:11:40.340 --> 00:11:46.100 and honestly, with the side-by-side comparisons, it is tough to tell the difference in image quality 00:11:46.100 --> 00:11:49.500 between the two models, like really tough. 00:11:49.500 --> 00:11:53.540 There are clear benefits in specific areas that NVIDIA points out, 00:11:53.540 --> 00:11:56.580 things like fences, power lines, and barbed wires, 00:11:56.580 --> 00:12:01.620 but there's still obvious artifacts when dealing with semi-transparent objects, 00:12:01.620 --> 00:12:07.300 or just very busy scenes. A lot of the artifacts are different than DLSS3, 00:12:07.300 --> 00:12:11.660 but are still present. On the bright side, at least on high-end cards, 00:12:11.660 --> 00:12:15.900 the transformer models don't show a substantial performance hit. 00:12:15.900 --> 00:12:19.300 Enough theory, I wanna talk about MF-ing G. 00:12:19.300 --> 00:12:23.580 Multi-frame Gen is perhaps the most game-changing tech landing with these new cards. 00:12:23.580 --> 00:12:27.940 Like the previous version of Framegen, it uses AI to generate in-between frames 00:12:27.940 --> 00:12:32.700 based on optical flow data and rendered frames, but Multi-frame Gen now allows users 00:12:32.700 --> 00:12:35.980 to generate up to three in-betweens, rather than just one, 00:12:35.980 --> 00:12:39.300 boosting frame rates to up to four times native. 00:12:39.300 --> 00:12:43.980 Does it work? Well, according to our charts, yes, very yes. 00:12:43.980 --> 00:12:49.420 The numbers double, triple, and quadruple, and make the 5090 look absolutely ridiculous, 00:12:49.420 --> 00:12:52.620 at least in the charts. But as big as that bar is, 00:12:52.620 --> 00:12:56.420 the real frames haven't changed. So what's the deal? 00:12:56.420 --> 00:13:01.540 Well, MFG's pretty wild. DLSS3 Framegen required specific optical flow 00:13:01.540 --> 00:13:05.380 accelerating hardware on GPUs, and combined that with the game data, 00:13:05.380 --> 00:13:09.660 like depth and motion vectors to generate in-between frames. And it was an okay solution, 00:13:09.660 --> 00:13:13.900 but you had to have two bits of hardware processing each frame, 00:13:13.900 --> 00:13:17.520 and that's just inefficient, and could even cause the GPU to throttle, 00:13:17.520 --> 00:13:20.620 resulting in a lower base frame rate to multiply off of. 00:13:20.660 --> 00:13:24.380 That's why you didn't just see a straight doubling of frame rate when you turned Framegen on. 00:13:24.380 --> 00:13:28.500 The 5090 and multi-FrameGen is Shu Aida's optical flow accelerator, 00:13:28.500 --> 00:13:32.620 and instead utilized tightly integrated Tensor and CUDA cores in Blackwell 00:13:32.620 --> 00:13:35.660 to run a lightweight AI optical flow model. 00:13:35.660 --> 00:13:39.980 Not hardware accelerated, it's just an AI model. This means that single Framegen 00:13:39.980 --> 00:13:43.980 should now run 40% faster while using 30% less VRAM. 00:13:43.980 --> 00:13:48.700 We know it works, but how does it look? Well, it depends on who you ask. 00:13:48.700 --> 00:13:51.820 If you want to see your FPS number much higher then it works great. 00:13:51.820 --> 00:13:56.900 Nothing else sort of hacking your FPS counter will let you get nearly 600 FPS in Cyberpunk. 00:13:56.900 --> 00:14:00.860 But visually, it's not perfect, and Framegen weirdness still persists. 00:14:00.860 --> 00:14:05.260 Look at the combing on these crosswalks in Cyberpunk, or this bottle phasing in and out in the benchmark, 00:14:05.260 --> 00:14:09.140 or the doubling of the fan blades in these large HVAC units. In Alan Wake 2, 00:14:09.140 --> 00:14:12.900 there's obvious artifacting around the player model and around the edge of your flashlight, 00:14:12.900 --> 00:14:17.500 which is sadly exactly where you will be looking 100% of the time. 00:14:17.500 --> 00:14:22.100 And it's worth noting that these artifacts are not present when we're just using DLSS for upscaling. 00:14:22.100 --> 00:14:26.780 Curiously, while Cyberpunk and Alan Wake were both updated with explicit support for multi Framegen, 00:14:26.780 --> 00:14:30.780 the feature can be forced in any DLSS3 single Framegen 00:14:30.780 --> 00:14:36.340 supported games through the NVIDIA driver. And the game that fared the best was Dragon Age of Veilguard. 00:14:36.340 --> 00:14:39.740 The world's full of magic, so who's to say exactly what a vortex of shadow 00:14:39.740 --> 00:14:44.220 is supposed to look like? And since it already ran at a solid 70 FPS 00:14:44.220 --> 00:14:48.820 with all the settings cranked, no Framegen, it kept input latency manageable, 00:14:48.820 --> 00:14:52.860 which is really important, because if your base FPS is only 30 frames, 00:14:52.860 --> 00:14:57.220 well, Framegen will make it look smooth, but you'll observe many visual anomalies, 00:14:57.220 --> 00:15:01.060 and latency is still dictated by your true frame rate, 00:15:01.060 --> 00:15:05.460 meaning that the game feels far less responsive than it looks like it should be. 00:15:05.460 --> 00:15:09.460 The good news, says NVIDIA, is that MFG at least isn't adding any latency 00:15:09.460 --> 00:15:13.500 compared to the base frame rate, but we felt like it would be a good idea to verify that. 00:15:13.500 --> 00:15:17.700 And verify we did, using our trusty LDAT, our click to photon test results 00:15:17.700 --> 00:15:22.260 showed that Framegen does not increase latency over native with reflex on. 00:15:22.260 --> 00:15:25.300 In fact, it seems to actually lower the latency slightly. 00:15:25.300 --> 00:15:28.420 It doesn't really make sense to us, so we're gonna chalk that up to sampling error, 00:15:28.420 --> 00:15:32.580 but if there is any effect on latency, it's so minor that it's not noticeable 00:15:32.580 --> 00:15:36.180 compared to our total system latency, and that is mighty impressive. 00:15:36.180 --> 00:15:40.260 But the issue remains, you can't beat your base frame rate's latency, 00:15:40.260 --> 00:15:44.860 and when it's disconnected from the motion you see on screen, it almost makes it worse. 00:15:44.860 --> 00:15:48.340 Perhaps the situation will improve with reflex too, but that's not here yet, 00:15:48.340 --> 00:15:51.500 so we aren't gonna dwell on it, even if the tech is really cool. 00:15:51.500 --> 00:15:55.620 Our take on multi-frame gen right now is that it has the same key flaws before. 00:15:55.620 --> 00:15:58.740 It's a win more feature that works the best 00:15:58.740 --> 00:16:03.420 when it makes the least sense to use, which means it is definitely not the silver bullet 00:16:03.420 --> 00:16:06.940 that NVIDIA's graphs make it out to be. With all this power, 00:16:06.940 --> 00:16:11.820 it would make a lot more sense to use the 5090 to make some money, right? So let's talk productivity. 00:16:11.820 --> 00:16:16.340 Hey, you might not know me, but I do this kind of thing and this kind of thing. 00:16:16.340 --> 00:16:19.340 And NVIDIA's new architecture has benefits for me too. 00:16:19.340 --> 00:16:22.660 The encoder and decoders provide support for 422 chroma sampling, 00:16:22.660 --> 00:16:27.740 which will make working with high-end video files much faster, especially for multi-camera video edits. 00:16:27.740 --> 00:16:31.220 The encoders also provide better quality at smaller file sizes. 00:16:31.220 --> 00:16:36.460 Sadly, we can't verify that for you today as we are currently re-evaluating our encoding benchmarks, 00:16:36.460 --> 00:16:40.220 but the new media engine is almost certainly playing a role in Puget Bench, 00:16:40.220 --> 00:16:43.540 where we see a nice 9% bump in Premiere Pro performance 00:16:43.540 --> 00:16:47.500 and an even nicer, nearly 20% improvement DaVinci Resolve 00:16:47.500 --> 00:16:51.140 when compared to the 4090. In Blender, NVIDIA has us considering 00:16:51.140 --> 00:16:55.140 finding a new benchmark as the 5090 has brought Barbershop render times 00:16:55.140 --> 00:16:59.100 to less than half a minute, more than double the speed of the 3090 Ti. 00:16:59.100 --> 00:17:03.820 Nice. Overwrought editing transition here. Double the 3090 Ti, you say? 00:17:03.820 --> 00:17:08.900 AI nerds, rejoice! If you're like me and for your sake, I hope you're not, 00:17:08.900 --> 00:17:12.380 you've been dying for NVIDIA to release a new 32-gig consumer card. 00:17:12.380 --> 00:17:17.700 So with all the bragging NVIDIA's been doing about AI tops, I'm expecting some big numbers. 00:17:17.700 --> 00:17:22.340 And in the Procyon text benchmarks, what the fuck? Number is not big. 00:17:22.340 --> 00:17:27.260 Sure, the 5090 is still the best card on the charts, but I was expecting more than this. 00:17:27.260 --> 00:17:30.620 We'll see roughly 20 to 30% improvement over the 4090, 00:17:30.620 --> 00:17:35.180 depending on the benchmark, and 60 to 70% over the 3090 Ti. 00:17:35.180 --> 00:17:40.060 I can see why they keep talking about AI tops and not specific performance. 00:17:40.060 --> 00:17:44.580 In ML Perf, the story remains largely the same in the time to first token 00:17:44.580 --> 00:17:50.020 and the token generation rate benchmarks. For image generation, our preferred Procyon benchmark 00:17:50.020 --> 00:17:54.620 doesn't support the 5090 yet. So we tested using the benchmark provided by NVIDIA. 00:17:54.620 --> 00:18:00.260 Prepare your salt grains for the taking. In the Procyon Flux FP8 image generation, 00:18:00.260 --> 00:18:03.780 the 5090 leads by a margin in line with the rest of our benchmarks. 00:18:03.780 --> 00:18:08.500 But when we switch to FP4 precision, the 5090 shows how powerful the native hardware support 00:18:08.500 --> 00:18:13.420 can be, taking less than one quarter of the time to generate images compared to the 4090. 00:18:13.420 --> 00:18:17.900 We'd love to see how this fairs against the 3090 Ti, but this NVIDIA provided benchmark 00:18:17.900 --> 00:18:21.440 doesn't support older cards. I was expecting AI to be the place 00:18:21.440 --> 00:18:24.620 where this card really shines, but I guess potential buyers will have to settle 00:18:24.620 --> 00:18:29.140 for just having the best consumer friendly grade card for AI. 00:18:29.140 --> 00:18:34.460 We'll call it the nifty feinty. Somehow there is still more review to go. 00:18:34.460 --> 00:18:39.660 Good thing this is so digestible and uncomplicated so far, right? Blackwell's main efficiency improvements over ADA 00:18:39.660 --> 00:18:42.660 seem to come from what they're calling Max-Q functionality. 00:18:42.660 --> 00:18:46.220 It boils down to a few small but significant changes. 00:18:46.220 --> 00:18:50.360 Improvements to power gating, thanks to an additional power rail and improved logic 00:18:50.360 --> 00:18:54.080 allows more of the GPU to switch to a low power state more rapidly. 00:18:54.080 --> 00:18:57.660 In CPU bound or frame cap scenarios, this could help save some power, 00:18:57.660 --> 00:19:01.540 especially on mobile chips. But in GPU bound full load scenarios, 00:19:01.580 --> 00:19:06.520 this monster will absolutely draw its fully rated 575 watts, 00:19:06.520 --> 00:19:10.940 including transient spikes of as high as 637 watts. 00:19:10.940 --> 00:19:14.900 And you can see even in real world gaming, it will pull space heater levels of power 00:19:14.900 --> 00:19:18.620 with an average of 554 watts in F124. 00:19:18.620 --> 00:19:22.460 And to manage all that power, they had to make a unique cooler design. 00:19:22.460 --> 00:19:26.100 While everyone else was making four slot behemoths, NVIDIA built something very different. 00:19:26.100 --> 00:19:30.660 And man, does it look good. Not only is it classy, it's also innovative. 00:19:30.700 --> 00:19:34.700 Over ambitious even. The main board of the video card is just the middle section 00:19:34.700 --> 00:19:39.500 and the outputs in PCIe connector are on daughter boards connected via what they call a flexible PCB. 00:19:39.500 --> 00:19:44.220 It's like a stiff ribbon cable, I guess. This allows for a double flow through design 00:19:44.220 --> 00:19:50.380 with fans blowing through dense heat sinks. Anecdotally, the fans run quiet, too quiet even. 00:19:50.380 --> 00:19:54.660 So like the 4090, most of the time, the loudest thing about the card will be its coil wine. 00:19:54.660 --> 00:20:00.420 It's not the worst we've heard, but it's noticeable. And if you expected it to run cooler than the 4090 founders, 00:20:00.420 --> 00:20:05.580 it doesn't. But given how much smaller it is, not to mention the enormous thermal load it's dealing with, 00:20:05.580 --> 00:20:10.060 I'd say it's doing a great job. But the new cooler style brings new build considerations. 00:20:10.060 --> 00:20:13.540 We know that flow through coolers can have a noticeable impact on CPU temps, 00:20:13.540 --> 00:20:17.300 especially for those using tower heat sinks. So as a double flow through, double bad, 00:20:17.300 --> 00:20:21.340 we took the 5090 and the 4090 FE and put them in a Corsair 4000D. 00:20:21.340 --> 00:20:24.500 And even with both running at 450 Watts to control the experiment, 00:20:24.500 --> 00:20:29.100 our poor Noctua NHD15 saw CPU temps that are roughly three degrees higher 00:20:29.140 --> 00:20:34.300 in both synthetic and gaming workloads. A CPU cooler upgrade, perhaps an intake-mounted radiator, 00:20:34.300 --> 00:20:38.220 could be in order for some folks. Wow, that was a lot to talk about. 00:20:38.220 --> 00:20:41.500 So what's our conclusion? Well, if you're a professional game developer 00:20:41.500 --> 00:20:45.780 or any other professional, or basically anyone who can use the new performance 00:20:45.780 --> 00:20:48.820 and especially the new features to make money, 00:20:48.820 --> 00:20:52.900 it's a no-brainer. As for the gamers, well, if the 4090 was stupid, 00:20:52.900 --> 00:20:57.540 stupid price, but stupid performance, the 5090 is stupider. 00:20:57.540 --> 00:21:03.660 It provides 30-ish percent more performance by using 33% more hardware and 30-ish percent more power, 00:21:03.660 --> 00:21:08.980 and it gets a roughly 25% price increase. It's a 4090 plus plus. 00:21:08.980 --> 00:21:13.060 On the one hand, you could look at this and say, wow, this doesn't look good 00:21:13.060 --> 00:21:16.380 for the rest of the 50 series lineup, but it's also worth considering 00:21:16.380 --> 00:21:19.380 that the 4090 was kind of an outlier for 40 series, 00:21:19.380 --> 00:21:24.340 offering a huge boost over its predecessor with the rest offering smaller upgrades. 00:21:24.340 --> 00:21:28.820 So if you're on 30 series and still not in the mega, mega baller income bracket, 00:21:28.820 --> 00:21:34.180 I guess all we can do is wait and see. See if Lydus has the strength to do the segue. 00:21:34.180 --> 00:21:39.180 Who are you? If you like this video, 00:21:39.180 --> 00:21:43.540 check out the one you get on ACCS chronging, 00:21:43.540 --> 00:21:45.740 watch this good nugget for now. 00:21:46.980 --> 00:21:49.660 I wish I could eat a nugget right now.