Comparison Asus Radeon RX 9070 TUF Gaming OC 16GB vs Asus Radeon RX 9070 XT OC TUF Gaming 16GB

A GPU is a type of graphics processor that determines the fundamental performance characteristics of a video adapter. Today there are two main manufacturers - AMD and NVIDIA. Intel has also entered the leadership race with its Intel Arc (A-Series, B-Series) line of discrete graphics.

NVIDIA: GeForce GT 1030, GeForce GTX 1050 Ti, GeForce GTX 1060, GeForce GTX 1070, etc. (all related to GeForce 10 series), GeForce GTX 1630, GeForce GTX 1650( SUPER), GeForce GTX 1660( SUPER, Ti), GeForce RTX 20 series, namely GeForce RTX 2060( SUPER), GeForce RTX 2070( SUPER), GeForce RTX 2080( SUPER, Ti), GeForce RTX 3050, GeForce RTX 3060, GeForce RTX 3060 Ti, GeForce RTX 3070, GeForce RTX 3070 Ti, GeForce RTX 3080, GeForce RTX 3080 Ti, GeForce RTX 3090, GeForce RTX 3090 Ti, GeForce RTX 4060, GeForce RTX 4060 Ti, GeForce RTX 4070, GeForce RTX 4070 SUPER, GeForce RTX 4070 Ti, GeForce RTX 4 070 Ti SUPER, GeForce RTX 4080, GeForce RTX 4080 SUPER, GeForce RTX 4090, GeForce RTX 5060, GeForce RTX 5060 Ti, GeForce RTX 5070, GeForce RTX 5070 Ti, GeForce RTX 5080, GeForce RTX 5090, as well as professional Quadro.

AMD: Radeon RX 500 series as Radeon RX 550, Radeon RX 560, Radeon RX 570, Radeon RX 580, Radeon RX 590, Radeon RX 5500 XT, Radeon RX 5600 XT, Radeon RX 5700, Radeon RX 5700 XT, Radeon RX 6400, Radeon RX 6500 XT, Radeon RX 6600, Radeon RX 6600 XT, Radeon RX 6650 XT, Radeon RX 6700 XT, Radeon RX 6750 XT , Radeon RX 6800, Radeon RX 6800 XT, Radeon RX 6900 XT, Radeon RX 6950 XT, Radeon RX 7600, Radeon RX 7600 XT, Radeon RX 7700 XT, Radeon RX 7800 XT, Radeon RX 7900 XT, Radeon RX 7900 XTX, Radeon RX 7900 GRE, Radeon RX 9070, Radeon RX 9070 XT, Radeon RX Vega 56, Radeon RX Vega 64, AMD Radeon VII and professional FirePro.

Knowing the GPU model, you can find detailed information on it (special specs, reviews, reviews, etc.) and evaluate how suitable this board is for your purposes. It is worth noting that in video cards from third-party brands, the characteristics of the graphics processor may differ slightly from the standard ones (and often in the direction of acceleration and improvement).

The number of stream processors provided by the graphics card.

A stream processor is a separate part of the GPU, designed to execute one shader at a time. Shaders, in turn, are small programs responsible for creating individual graphic effects (for example, surface gloss, glare on the surface of water, motion blur, etc.). Accordingly, the more stream processors provided in the design, the more shaders the graphics card can simultaneously execute and the higher its computing power. However, in general, this is a rather specific parameter, relevant mainly for professional developers, modders and enthusiastic gamers.

Tensor cores in graphics cards are specialized computing units designed to accelerate tasks related to artificial intelligence, machine learning, and neural network processing. They are used for technologies like DLSS (Deep Learning Super Sampling), which enhances image resolution without a significant increase in load, as well as for accelerating rendering and calculations in scientific and professional applications. Unlike traditional CUDA cores, tensor cores are optimized for matrix operations, allowing for a significant increase in performance in tasks that require deep neural processing. The more tensor cores there are, the higher the data processing speed, although in gaming, an excessive number of them is not always justified, unlike in professional tasks.

RT Cores (Ray Tracing Cores) are specialized computational units in NVIDIA graphics cards that accelerate ray tracing. They simulate realistic reflections, shadows, and lighting, offloading the primary CUDA cores. The number of RT Cores in a graphics card determines how quickly it can perform ray tracing. The more RT Cores, the higher the performance when Ray Tracing is enabled. For example, the RTX 4060 Ti has only 32 RT Cores, while the RTX 4090 has 128, providing a significant speed boost in rendering complex scenes. In ray-traced games like Cyberpunk 2077 or Alan Wake 2, a larger number of RT Cores allows for processing reflections, shadows, and global illumination with less FPS drop. In professional tasks, such as in Blender or Omniverse, RT Cores speed up rendering, reducing frame processing time. For 1080p gaming, 32–48 RT Cores are sufficient, while for 1440p and 4K, 64–128 are preferable.

The result shown by the graphics card in the test (benchmark) Passmark G3D Mark.

Benchmarks allow you to evaluate the actual capabilities (primarily overall performance) of a graphics card. This is especially convenient in light of the fact that adapters with similar characteristics in fact can differ markedly in capabilities (for example, due to the difference in the quality of optimization of individual components for joint work). And Passmark G3D Mark is the most popular benchmark for graphics adapters nowadays. The results of such a test are indicated in points, with a higher number of points corresponding to better performance. As of mid-2020, the most advanced graphics cards can score over 17,000 points.

Note that Passmark G3D Mark is used not only for general performance evaluation, but also to determine the compatibility of a graphics card with a specific processor. The CPU and graphics adapter must be approximately equal in terms of the overall level of computing power, otherwise one component will “pull back” the other: for example, a weak processor will not allow a powerful gaming graphics card to unleash the full potential. To search for a video adapter for a specific CPU model, you can use the list "Optimal for AMD processors" or "Optimal for Intel processors" in the selection of our catalog.

Format of additional power required for the operation of the graphics card.

By itself, the PCI-E connector, which is standardly used to connect video cards, provides 75 watts of power. For many models, even quite performant ones, this is quite enough, and many modern video adapters do without additional power. However, models with additional power have become more widespread, especially among high-end solutions.

The simplest version of such a power supply is one 6-pin or 8-pin connector. A 6-pin connector can additionally provide up to 75 watts, an 8-pin connector can provide up to 150 watts. However, for high-end solutions, one connector is not enough, so there are models with 6 + 8 pin, 8 + 8 pin, and even 8 + 8 + 6 pin or 8 + 8 + 8 pin formats.And the new cards are completely 16-pin. Such power connectors have a total of 16 lines: 12 for current supply and 4 signal. The effective power threshold of the 16 pin connector is up to 600 watts. Connection to it can be done through a 3×8 pin adapter.

Note that it is theoretically possible to connect a 6-pin power supply to an 8-pin connector and vice versa, even corresponding adapters are availa...ble for this. However, in fact, the possibility of such a connection should be clarified separately, and such tricks should be used only in extreme cases, when other options are not available.

The smallest power supply recommended for a computer with this graphics card.

This parameter, usually, is much higher than the power consumption of the graphics card itself. This is natural — after all, the PSU must provide electricity to the entire system, not just the video adapter. At the same time, the higher the power of the graphics card, the inevitably higher the power consumption of the PC as a whole. Moreover, this is due not only to the “voracity” of the graphics adapter itself, but also to the consumption of other PC components: a high-end graphics card, usually, is combined with an equally powerful (and energy-intensive) system.

With this in mind, manufacturers indicate the minimum recommended power supply. Of course, such recommendations are not mandatory; however, when using a PSU with a power lower than the recommended one, the probability of malfunctions increases significantly — to the point that even a very limited system may simply “not start”.