From Wikipedia, the free encyclopedia
Series of GPUs by Nvidia
This article is about GeForce models numbered as RTX 50XX. For models numbered as 5XXX, see
GeForce FX series.
GeForce RTX 50 seriesA GeForce RTX 5090 Founders Edition released in 2025, the series'
flagship model Release date January 30, 2025 (2025-01-30) Manufactured by TSMC Designed by Nvidia Marketed by Nvidia Architecture Blackwell Fabrication process TSMC 4N[1] Entry-levelThe GeForce RTX 50 series is a series of consumer graphics processing units (GPUs) developed by Nvidia as part of its GeForce line of graphics cards, succeeding the GeForce 40 series. Announced at CES 2025, it debuted with the release of the RTX 5080 and RTX 5090 on January 30, 2025. It is based on Nvidia's Blackwell architecture featuring Nvidia RTX's fourth-generation RT cores for hardware-accelerated real-time ray tracing, and fifth-generation deep-learning-focused Tensor Cores. The GPUs are manufactured by TSMC on a custom 4N process node.
In March 2024, Nvidia announced the Blackwell architecture for its datacenter products. Like Ampere, Blackwell is a shared architecture between both consumer and datacenter products rather than distinct architectures released simultaneously like Ada Lovelace for consumers and Hopper for datacenter.
At the Game Awards in December 2024, a cinematic trailer for The Witcher IV was shown which had been pre-rendered on an "unannounced Nvidia GeForce RTX GPU". This was assumed to be an upcoming GeForce RTX 50 series GPU.[2][3] Following the RTX 50 series announcement, Nvidia confirmed that the trailer was "pre-rendered in Unreal Engine 5 on a GeForce RTX 5090".[4] Later in the same month, it was reported that Nvidia had begun stockpiling GeForce RTX 50 series units in U.S. warehouses due to a looming 10% import tariff and 60% tariff on Chinese imports[5][6] that Donald Trump promised in his re-election campaign.[7][8]
Nvidia CEO Jensen Huang presenting the RTX 5070 Laptop at CES 2025On January 6, 2025, the GeForce RTX 50 series was officially announced for both desktop and mobile devices during Nvidia's CES keynote in Las Vegas.[9] The pricing announcement was met with surprise as the RTX 5080 at $999 was the same price that the RTX 4080 Super released at a year earlier despite the anticipated price increases.[10] Nvidia CEO Jensen Huang falsely[11][12] claimed that the RTX 5070 could reach "RTX 4090 performance at $549" despite a heavy reliance on DLSS 4 upscaling and Multi Frame generation rather than raw performance.[13]
The printed circuit boards of the RTX 5080 and 5090 (top and bottom views) Blackwell architecture[edit]The GeForce RTX 50 series is powered by the Blackwell microarchitecture which continues Ada Lovelace's emphasis on high graphics frequencies and large L2 caches. The Blackwell architecture introduces Nvidia RTX's fourth-generation RT cores for hardware-accelerated real-time ray tracing and fifth-generation Tensor Cores for AI compute and performing floating-point calculations.[14]
RTX 50 series GPUs are the first consumer GPUs to feature GDDR7 video memory for greater memory bandwidth over the same bus width compared to the GDDR6 and GDDR6X memory used in the GeForce 40 series. RTX 50 series desktop GPUs use GDDR7 modules from Samsung due to them being available for validation earlier than modules from SK Hynix and Micron.[15][16]
The GeForce RTX 50 series uses the 16-pin 12V-2×6 connector which is a revision of the 12VHPWR connector featured on the GeForce 40 series. There were problems with the 12VHPWR connector melting on some RTX 4090 GPUs due to the connector not being fully seated and connector design flaws that did not implement a high enough safety and error tolerance.[17] The 12V-2×6 connector revision, published by PCI-SIG in July 2023, addressed this by shortening the four sense pins so the connector will not push any power if it has not been fully seated.[18] The 12VHPWR design would still draw up to 150W of power even if the sense pins were not making full contact. 12V-2×6 is backwards compatible with existing 12VHPWR cables and adapters.
Nvidia has mandated to its AIB partners that the 16-pin 12V-2×6 connector be used on all RTX 50 series designs.[19] With the GeForce 40 series, the 12VHPWR connector was only mandated on higher power cards such as the RTX 4070 Super, RTX 4070 Ti, RTX 4070 Ti Super, RTX 4080, RTX 4080 Super and RTX 4090 while RTX 4060, RTX 4060 Ti and RTX 4070 AIB designs had the option of using 8-pin PCIe connectors. The 600W-capable 12VHPWR connector would not have been necessary on sub-200W cards.
The fourth generation of Deep Learning Super Sampling (DLSS) was unveiled alongside the RTX 50 series. DLSS 4 upscaling uses a new vision transformer-based model for enhanced image quality with reduced ghosting and greater image stability in motion compared to the previous convolutional neural network (CNN) model.[20] DLSS 4 also allows a greater number of frames to be generated and interpolated based on a single traditionally rendered frame. This form of frame generation called Multi Frame Generation is exclusive to the RTX 50 series while the GeForce 40 series is limited to one interpolated frame per traditionally rendered frame. Nvidia claims that DLSS 4's frame generation model uses 30% less video memory with the example of Warhammer 40,000: Darktide using 400 MB less memory at 4K resolution with frame generation enabled.[21] Nvidia claims that 75 titles will integrate DLSS 4 Multi Frame Generation at launch, including Alan Wake 2, Cyberpunk 2077, Indiana Jones and the Great Circle, and Star Wars Outlaws.[22]
Media Engine and I/O[edit]The RTX 50 series includes DisplayPort 2.1b UHBR20 (80Gbps) with higher display output data rates to support high resolution and high refresh rate displays.[23] The GeForce 40 series received criticism for only including DisplayPort 1.4a (32Gbps) while the competing Radeon RX 7000 series included DisplayPort 2.1 UHBR13.5 (54Gbps). At CES 2025, VESA announced a collaboration with Nvidia on the new DP80LL ("low loss") UHBR20 active cable standard.[24] DP80LL allows for 80Gbps DisplayPort 2.1 cables up to 3 meters long as passive DP80 cables are limited in length due to signal integrity concerns.
The RTX 50 series introduces the ninth-generation NVENC encoder and sixth-generation NVDEC video decoder. For the first time in a consumer GeForce GPU, support is adding for encoding and decoding video in the 4:2:2 color format for professional-grade higher color depth.[25]
From left to right: GeForce RTX 5070, 5080 and 5090 Founders Editions at CES 2025 CUDA Cores and Memory Bandwidth per USD for RTX 50-seriesGeForce RTX 50 series desktop GPUs are the second consumer GPUs to utilize a PCIe 5.0 interface[26] and the first to feature GDDR7 video memory (except for the entry level RTX 5050 that still uses GDDR6).[27] They are fabricated by TSMC using a custom 5 nm process dubbed 4N.[28][29]
Laptops featuring GeForce RTX 50 series laptop GPUs were shown at CES 2025. Laptops with RTX 50 series GPUs were paired with Intel's Arrow Lake-HX and AMD's Strix Point and Fire Range CPUs.[37][38] Nvidia claims that Blackwell architecture's new Max-Q features can increase battery life by up to 40% over GeForce 40 series laptops.[39] For example, Advanced Power Gating saves power by turning off areas of the GPU that are unused and the paired GDDR7 memory can run in an "ultra" low-voltage state.[40] Initial RTX 50 series laptops will become available in March 2025 starting at $1,299.[41]
The 12V-2x6 connector used by the RTX 5090 Founders Edition (FE) faces criticism due to a design flaw that can cause the connector to melt and catch fire. The flaw can potentially cause overheating, melting, and fire. These flaws are currently only present on the RTX 5090 FE[49][50][51] and RTX 5080 FE[citation needed] and are similar to the failures seen on the RTX 40 series.
Availability and pricing[edit]The releases of the RTX 5090, 5080 and 5070 Ti were marred by severe availability issues and pricing well above MSRP.[52][53][54][55][56]
CUDA, OpenCL, and PhysX 32-bit support removal[edit]Support for 32-bit PhysX, OpenCL, and CUDA applications was dropped in the GeForce RTX 50 series, which caused negative reactions from numerous gaming communities.[57][58][59][60][61] Around fifty games are now unplayable with PhysX enabled on the 50 series without an additional Nvidia GPU that still supports 32-bit CUDA.[citation needed]
Incomplete dies / missing ROPs[edit]The dies of certain RTX 5090/5090D, 5080, and 5070 Ti cards have been found to be missing eight render output units (ROPs), resulting in a performance loss in graphics while pure compute and AI workloads are unaffected.[62][63] In a statement to the press Nvidia confirmed the issue, and claimed that less than 0.5% of the respective cards are affected and that the "production anomaly" has been rectified.[64][65]
Black screen issues[edit]Some RTX 5080 and 5090 users reported an issue where the system would boot into a black screen after installing Nvidia drivers. Nvidia confirmed the issue and said that a new driver update would fix it for people who hadn't received a VBIOS update yet.[66][67] Released on February 27, 2025 Nvidia drivers version 572.60 claim to have fixed the issue.[68][69] Nvidia has since released multiple hotfix and Game Ready drivers that contain additional fixes for the issue.[70][71]
Windows driver branch quality and stability[edit]Media outlets have complained about the quality and stability of the 572.XX and 576.XX Windows driver branch (that was released for the RTX 50 series) affecting previous generation Nvidia GPUs including RTX 30 and RTX 40 series.[72][73][74][75][76][77][78]
Controversial RTX 5060 Ti 8GB and RTX 5060 review restrictions[edit]Nvidia decided not to source reviewers with RTX 5060 Ti 8GB cards and prevented certain partners from doing so as well. The company also left reviews of the RTX 5060 in the air as the review embargo was lifted on April 16, 2025 before reviewers could source the cards officially.[79][80][81][82]NVIDIA chose not to sample the RTX 5050 as well.[83][84]
DLSS 4 Multi Frame Generation (MFG) criticism[edit]The technology press has been highly critical of Nvidia's performance claims relating to GeForce RTX 50 graphics cards.[85][86][87][88]
Nvidia claims that the RTX 5070 is as fast as the RTX 4090, but this is untrue except the extreme scenario of 4x DLSS 4 Multi Frame generation and the lowest quality DLSS preset. This combination results in noticeable visual artefacts which are exacerbated if the base frame rate is too low; this is said to be between 40 and 60 fps by several reviewers. Additionally, while it may improve perceived frame rate through frame smoothing, it increases input latency and is thus unsuitable for latency-sensitive games such as competitive shooters, fighting games and virtual reality games.
Nvidia also claims that the RTX 5060 Ti is up to 50 times faster than the GTX 1060, a GPU released 9 years prior and with a significantly lower MSRP than the 5060 Ti. These performance claims appear to be based on the 1060's lack of support for hardware ray tracing, DLSS Super Sampling, and Multi Frame Generation; as such, they are of little relevance when evaluating the gaming performance of the 5060 Ti.[89]
Size comparison between the RTX 5090 FE (right) and its predecessor, the RTX 4090 FE (left)The RTX 5090 received a generally lukewarm reception,[90][91][92][93] citing its overreliance on AI to find its value, the card requiring 125W more than the RTX 4090 (which is rated at 450W), and being significantly more expensive at $1999 than the RTX 4090, which had an MSRP of $1599.[94] Many reviewers called the RTX 50 series marketing deceitful, considering that DLSS 4's Multi Frame Generation cannot make unplayable games playable, and cannot improve latency. Some reviewers even jokingly referred to it as the "RTX 4090 Ti".[95]
Antony Leather from Forbes described the RTX 5080 as "a decent upgrade from anything below or older than the RTX 4080 Super and 4080".[96] However, he criticized that "there's only a 10% uplift over the RTX 4080 Super" in raw performance, with the RTX 4090 still being "quite a bit faster" without Multi Frame Generation, while the RTX 5080 only just overtakes the RTX 4090 with Multi Frame Generation enabled.[96]
Andrew Cunningham from Ars Technica stated that the RTX 5080 "is the third-fastest GPU on the market [behind the RTX 5090 and RTX 4090], but it's far short of the 4090, and it performs more like a second refresh of 2022's RTX 4080".[97] He praised the RTX 5080's MSRP of US$999 and described it as a "good 4K card", but called it "[b]arely an upgrade over the RTX 4080 Super".[97]
IGN praised the RTX 5080's overall performance, modest increase in power demand over its predecessor, and MSRP, though noted that "[i]t's [...] not quite the performance uplift that hardcore enthusiasts who upgrade every generation are going to want to see".[98] Also, while the 16 GB of VRAM "should be enough memory for most people", "it would have been nice to see the RTX 5080 adopt the 24GB featured on the RTX 4090, especially since this GPU is being pitched as a 4K graphics card".[98]
The RTX 5070 Ti had a lukewarm reception just like the RTX 5090 and RTX 5080. While it was generally praised for its competitive performance at 1440P and 4K resolutions relative to previous generation graphics cards, it also received criticism, most commonly for the card normally only being available at $900 or above, despite Nvidia's listed MSRP of $750.[99]
Andrew Cunningham from Ars Technica called the RTX 5070 Ti "essentially an RTX 4080 that also supports DLSS Multi-Frame Generation". While the card was praised for its excellent overall performance and being capable of 4K gaming, it was criticized for its poor price-to-performance and mediocre performance uplift.[100] TechPowerUp's review of the RTX 5070 Ti found large performance gains relative to the RTX 4070 Ti, praising its performance relative to AMD's at-the-time flagship RX 7900 XTX, the new DLSS 4 Frame Generation technology, and its efficiency and performance, although it did also receive criticism for its inflated MSRP.[101] IGN praised the performance of the RTX 5070 Ti and its value relative to the RTX 5090 and RTX 5080, stating "Not only is it the first RTX 5000 graphics card that provides a decent uplift over its predecessor, but it does so with a lower price tag than the $799 RTX 4070 Ti".[102] The RTX 5070 Ti was later criticized for being just as Powerful as the Competitors RX 9070 XT, which had an UVP almost 100$ Cheaper.
This section is empty.You can help by
adding to it.
(March 2025)The RTX 5060 Ti received moderate praise for its performance uplift over older RTX 4060 Ti and 3060 Ti cards,[103][104] although much attention was brought to the 8GB version's low VRAM capacity. According to Tom's Hardware, the 8GB version was unable to perform well at higher resolutions.[105]
The price $50 price difference between the 5060 Ti 8GB and 16GB versions, in contrast to the previous generation $100 difference between the RTX 4060 Ti 8GB and 16GB, led to a general preference for the 5060 Ti 16GB, although much like the other RTX 50 Series cards, the 5060 Ti suffered pricing much higher than MSRP. TechPowerUp's review of the card noted that "On paper, the 8 GB variant is supposed to be priced at $380, and the 16 GB variant at $430, but we now know that these prices are pure fiction. The RTX 5060 Ti 16 GB is realistically available from $500 mark, $70 higher than NVIDIA's starting price; while the RTX 5060 Ti 8 GB is priced closer to its natural MSRP".[106]
Like the 5060 Ti 8GB, the RTX 5060 is, according to Techspot limited by its 8GB VRAM capacity. Techspot's review stated that "It's frustrating how good the RTX 5060 could have been. Even with just 12 GB of VRAM, we might have been able to tentatively recommend it at its current price. With 16 GB, it could have been a genuinely solid product".[107]
James Archer from Rock Paper Shotgun described the RTX 5060 as an affordable option for 1080p, but "not equipped" for 1440p,[108] while Jacob Roach from XDA cited the Intel Arc B580 as "the one card that really kills the credibility of the RTX 5060", with its 12GB VRAM capacity. This despite the Arc B580 costing around $320 compared to the RTX 5060's $300 MSRP.[109]
This section is empty.You can help by
adding to it.
(June 2025)Trump is proposing an at least 10% blanket tariff on all imports, with tariffs as high as 60% on goods from China.
{{cite web}}: CS1 maint: numeric names: authors list (link){{cite web}}: CS1 maint: numeric names: authors list (link){{cite web}}: CS1 maint: numeric names: authors list (link)RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4
