NVIDIA GeForce RTX 5060 Ti 16GB Review in Spanish – Feat PNY OC Dual Fan

For NVIDIA there is no turning back, and it has decided that the new architecture Blackwell for graphics cards, employs more and better techniques and tools based on artificial intelligence, neural network processing, and generative AI engines. The green company seeks to further apply its expertise in enterprise AI, while also focusing on improvements in energy efficiency, compatibility with updated codecs, support for new video outputs, and progressive improvements in silicon architecture.

Still, Blackwell's star remains Deep Learning Super Sampling, popularly known as DLSS, which in its fourth generation promises to offer a considerable improvement in the frame rate per second compared to DLSS 3 and 3.5. In addition, advances such as neural shaders (Neural Shaders), AI-trained models to accelerate the creation of complex images without relying entirely on traditional ray tracing. Also included is a new version of DLSS Ray Reconstruction, the ray reconstruction technique that reduces the amount of calculations required to generate ray-traced lighting.

Let's start with the basics, the specifications of the graphics cards that we will show below.

La GeForce RTX 5060 Ti It is based on the new GPU GB200-2000, manufactured under TSMC's 4N process. It features 4,608 CUDA cores, 36 SMS (streaming multiprocessors) and a memory interface of 128 bitsThe card offers two memory configurations: 8 GB y 16 GB de GDDR7 at 28 Gbps, providing a bandwidth of 448 GB / s.

In this generation, they remain 4th generation RT cores y 5th generation Tensor Cores, with support for DLSS-4, Ray Reconstruction, Neural Shaders y RTX Video Super Resolution. Also included are improvements in energy efficiency and support for AV1 encoding and decoding, thanks to the ninth and sixth generation NVENC/NVDEC respectively.

One of the most striking points is, without a doubt, the debut of GDDR7 graphics memory in NVIDIA's gaming GPUs. After two generations of cards with GDDR6X, NVIDIA will be debuting this generation of memory. 

Among the main improvements of GDDR7, Signaling technology is offered PAM3 which promises a better signal to noise ratio and doubles the density of independent channels, achieving greater memory bandwidth as well as greater energy efficiency.

Fifth-generation Tensor Cores now support the data format FP4, which requires less than half the memory thanks to a type of compression with virtually zero loss in quality compared to FP16.

Blackwell’s fourth-generation RT cores double the throughput of ray tracing test intersections, which is a high-frequency operation when generating RT images. Therefore, ray-traced frames are expected to be generated at a higher speed. Also included in this generation is a micromapping opacity engine, which helps reduce the amount of computational calculations in alpha shaders. Other dedicated ray tracing technologies include the use of mega geometry, a triangle group intersection engine, and linear scanning spheres for rendering fine geometry objects such as hair.

La “mega geometry” aims to increase geometric detail in applications that use ray tracing. In particular, for graphics engines such as Unreal Engine 5 that use more advanced level of detail systems, it allows the use of ray tracing with greater fidelity, improving the quality of shadows, reflections and indirect lighting.

Mega geometry is expected to be available on all platforms. APIs de DirectX12, Vulkan y OptiX 9.0. It will also be available on all RTX graphics cards from the Turing architecture, or the RTX 20 generation.

The Blackwell architecture implemented in this card maintains support for Shader Execution Reordering (SER) 2.0, helping to optimize parallel rendering processes. Support for technologies such as RTX Video HDR, RTX Dynamic Lighting, and techniques such as RTX Skin y Neural Radiance Cache, although with certain limitations in terms of performance compared to high-end cards.

The AI ​​Management Processor (AMP) is a context-programmable scheduler on the GPU that improves process scheduling in Windows, reducing the contextual load on the GPU. Using a RISC-V processor, AMP works with the Windows architecture to reduce latency and improve memory management, reducing CPU load for task scheduling and helping to reduce bottlenecks, while improving frame rates and multitasking in Windows. 

And as for graphics generation features, we finally come to DLSS 4, the crown jewel in Blackwell. NVIDIA promises multi-frame rendering with improved performance and lower memory usage than previous versions of the technology, along with improvements to existing DLSS techniques such as frame rendering, ray tracing, super-resolution, and deep learning antialiasing.

With the combination of improvements in hardware, architecture and software, they promise 40% faster frame rate than DLSS 3, using 30% less video memory, and a model that only needs to run once per frame. Optical flow frame generation is now AI-based instead of dedicated hardware, also reducing the cost of frame generation and integration. An inverted metering system or Flip Metering shifts frame rate logic to the display engine, allowing the GPU to improve the accuracy of display display timings.

DLSS Super Resolution (SR) Boosts performance by using AI to produce higher-resolution frames from lower-resolution input. DLSS samples multiple low-resolution images and uses motion data and feedback from previous frames to construct high-quality images. The final product of the Transformer model is more stable, with less ghosting, more moving image detail, and improved antialiasing compared to previous versions of DLSS. 

La Ray Reconstruction (RR) Improves image quality by using AI to generate additional pixels in ray-traced scenes. DLSS replaces manual denoisers with an AI network trained on NVIDIA supercomputers that generates higher-quality pixels between sampled rays. In ray-traced content, the Transformer model for RR further improves quality, especially in scenes with complex lighting. In fact, all common artifacts from typical denoisers are significantly reduced. 

Deep learning antialiasing (DLAA) Provides improved image quality through an AI-based anti-aliasing technique. DLAA uses the same super-resolution technology developed for DLSS, creating a more realistic, high-quality image at native resolution. The result is greater temporal stability, motion detail, and smoother edges in a scene.

Neural shaders are a technology NVIDIA is looking to introduce at Blackwell, unifying traditional shaders with the use of AI in parts of the rendering process, partially at first, and believed to be fully so in the future. Tensor cores are now accessible to graphics shaders combined with scheduling optimizations in SER 2.0 (Shader Execution Reordering) so that AI graphics with neural filtering capabilities and AI models, including generative AI, can run simultaneously in next-generation games.

Neural shaders allow us to train neural networks to learn efficient approximations of complex algorithms that calculate how light interacts with surfaces, decompress super-compressed video, predict indirect illumination from limited real data, and approximate subsurface light scattering. The potential applications of neural shaders are still largely unexplored, meaning that new applications may be found.

Among the other integrated techniques are the “RTX Neural Materials”. AI is used to replace the original mathematical model of a material or texture with an approximation, promising “cinema-quality” frames at gaming-grade speeds while using less video memory and fewer graphics card resources.

Another technique is RTX Neural Texture Compression, or neural texture compression, which leverages neural networks accessed through neural shaders to compress and decompress material textures more efficiently than traditional methods. Then we have the so-called “neural radiance cache,” or Neural Radiance Cache (NRC). This uses a neural shader to cache and approximate brightness information. Taking advantage of the By learning a neural network, complex lighting information can be stored and used to create high-quality global illumination and dynamic lighting effects in real time. 

From there we have RTX Skin, a technique that NVIDIA developed based on subsurface scattering for rendering cinematic images. This allows light passing through certain skin surfaces that aren't entirely solid to be rendered subtly or intensely, depending on the game's requirements, using ray tracing.

Y RTX Neural Faces, or neural faces, creates a raster face on top of which an approximate 3D layer is placed using a generative AI model, which can infer a result of natural-looking faces.

In terms of connectivity, the RTX 5060 Ti includes support for DisplayPort 2.1b y HDMI 2.1, allowing refresh rates of up to 480Hz in 4K y 165Hz in 8K, making it suitable for most current gaming monitors.

Finally, as regards energy consumption, the RTX 5060 Ti has a TGP of 180w, which represents a fairly acceptable efficiency compared to previous models such as the RTX 4060 Ti.

More detailed information can be found in the article on the Editor's Day held during CES 2025 in Las Vegas.