NVIDIA has finally laid to rest the last GeForce GPUs to feature the "GTX" brand extension, the GTX 16-series "Turing." Although two generations older than the current RTX 40-series "Ada," the GTX 16-series formed the entry-level for NVIDIA, with certain SKUs continuing to ship to graphics card manufacturers, and more importantly, notebook ODMs as popular GeForce MX and GTX 16-series SKUs. With NVIDIA introducing further cut-down variants of its "Ampere" based GA107 silicon, such as the desktop RTX 3050 6 GB, the company has reportedly discontinued the GTX 16-series. All its inventories are drained on NVIDIA's end, and the channel is expected to consume the last remaining chips in the next 1-3 months, according to a source on Chinese forum Broad Channels.

NVIDIA had originally conceived the GTX 16-series to form the lower half of its 2018 product stack, with the upper half driven by the RTX 20-series. Both are based on the "Turing" graphics architecture, but the GTX 16-series has a reduced feature-set, namely the lack of RT cores and Tensor cores. The idea at the time behind the GTX 16-series, was that at their performance levels, ray tracing would be prohibitively slow at any resolution, and so these could be left with just the CUDA cores of "Turing," and made to power games with pure raster 3D graphics, so gamers could at least benefit from the higher IPC and 12 nm efficiency of "Turing" over the 16 nm "Pascal." Popular GPU models include the GTX 1650, and the GTX 1660 Super.

KFA2, the EU-focused brand of graphics cards by Galax, today released the GeForce RTX 3050 6 GB EX, a somewhat premium take on the recently released entry-level GPU by NVIDIA. The KFA2 EX features a spruced up aluminium fin-stack heatsink that uses a flattened copper heatpipe to make broader contact with the GPU, and spread the heat better across the fin-stack. The 22.4 cm long card also has a couple of premium touches, such as a metal backplate, and RGB LED lighting. The lighting setup includes physical switch on the tail end of the card, with which you can turn it off. Also featured is idle fan-stop. The card offers a tiny factory overclock of 1485 MHz boost, compared to 1475 MHz reference. It sticks with PCIe slot power, there are no additional power connectors.

NVIDIA launched the GeForce RTX 3050 6 GB as its new entry level GPU. It is based on the older "Ampere" graphics architecture, and the 8 nm "GA107" silicon. It enables 18 out of 20 streaming multiprocessors physically present, which work out to 2,304 CUDA cores, 72 Tensor cores, 18 RT cores, 72 TMUs, and 32 ROPs. The 6 GB of 14 Gbps GDDR6 memory is spread across a narrower 96-bit memory bus than the one found in the original RTX 3050 8 GB. KFA2 is pricing the RTX 3050 6 GB EX at €199 including taxes.

NVIDIA today formally launched the GeForce RTX 3050 6 GB as its new entry-level discrete GPU. The RTX 3050 6 GB is a significantly different product from the original RTX 3050 that the company launched as a mid-range product way back in January 2022. The RTX 3050 had originally launched on the 8 nm GA106 silicon, with 2,560 CUDA cores, 80 Tensor cores, 20 RT cores, 80 TMUs, and 32 ROPs; with 8 GB of 14 Gbps GDDR6 memory across a 128-bit memory bus; these specs also matched the maximum core-configuration of the smaller GA107 silicon, and so the company launched the RTX 3050 based on GA107 toward the end of 2022, with no change in specs, but a slight improvement in energy efficiency from the switch to the smaller silicon. The new RTX 3060 6 GB is based on the same GA107 silicon, but with significant changes.

To begin with, the most obvious change is memory. The new SKU features 6 GB of 14 Gbps GDDR6, across a narrower 96-bit memory bus, for 168 GB/s of memory bandwidth. That's not all, the GPU is significantly cut down, with just 16 SM instead of the 20 found on the original RTX 3050. This works out to 2,048 CUDA cores, 64 Tensor cores, 16 RT cores, 64 TMUs, and an unchanged 32 ROPs. The GPU comes with lower clock speeds of 1470 MHz boost, compared to 1777 MHz on the original RTX 3050. The silver lining with this SKU is its total graphics power (TGP) of just 70 W, which means that cards can completely do away with power connectors, and rely entirely on PCIe slot power. NVIDIA hasn't listed its own MSRP for this SKU, but last we heard, it was supposed to go for $179, and square off against the likes of the Intel Arc A580.

The GeForce RTX 3050 has been around since January 2022, and formed the entry level of the company's RTX 30-series. It had its moment under the Sun during the crypto GPU shortage as a 1080p gaming option that sold around the $300 mark. With the advent of the RTX 40-series, NVIDIA is finding itself lacking an entry-level discrete GPU that it can push in high volumes. Enter the RTX 3050 6 GB. Cut down from the original RTX 3050, this SKU has 6 GB of memory across a narrower 96-bit GDDR6 memory interface, and fewer shaders. Based on the tiny GA107 "Ampere" silicon, it gets 2,048 CUDA cores compared to the 2,560 of the RTX 3050, a core-configuration NVIDIA refers to as the GA107-325. The card has a tiny typical graphics power (TGP) of just 70 W, and so we should see graphics cards without additional power connectors. The company plans to give the RTX 3050 6 GB a formal retail channel launch in February 2024, at a starting price of $179.

The lower mainstream graphics segment is considered to be the starting point for PC gaming, targeting 1080p gaming with medium-thru-high (though not extreme) settings, and popular e-sports titles at 1080p with high settings. This segment is preparing to see some action in the coming days, with the introduction of two new products, the Intel Arc A580, and a new 6 GB variant of the GeForce RTX 3050. We've seen the A580 "Alchemist" in development for a while now.

Based on the 6 nm ACM-G12 silicon, the Arc A580 comes with 24 Xe Cores, or 384 EU (execution units), which work out to 3,072 unified shaders, compared to the 3,584 of the A750, 4,096 of the A770, and the significantly lower 1,024 of the entry-level A380. The most interesting aspect of the A580 is its memory. Although 8 GB in size, it uses a wide 256-bit memory interface, and 16 Gbps memory speed, which works out to a generous 512 GB/s of bandwidth. The A580 also comes with a full PCI-Express 4.0 x16 host interface.

TechPowerUp today released the latest version of TechPowerUp GPU-Z, the popular PC graphics information, monitoring, and diagnostics utility. Version 2.52.0 adds support for AMD Radeon RX 7900 XTX, RX 7900 XT, RX 6300 OEM; NVIDIA GeForce RTX 4070 Ti, and a few rare "Ampere" based GPUs in circulation these days, including the RTX 3080 Ti 20 GB, RTX 3070 Ti based on GA102 silicon, RTX 3050 based on GA107, and the PCIe AIC version of the A800 80 GB accelerator. Detection is improved for the Xe LP-based iGPU of Intel Core "Raptor Lake" processors. NVIDIA GPUs with ECC memory now have ECC status reported in the Advanced panel. On GPUs where the boost frequency can't be read, the base frequency will be used to calculate fillrates. Clock speed detection for Intel Arc "Alchemist" GPUs has been improved. Vendor detection has been added for several new graphics card brands such as Corsair (gaming notebooks), Maxsun, and Wingtech.

DOWNLOAD: TechPowerUp GPU-Z v2.52.0

ASUS is giving final touches the to the TUF Gaming GeForce RTX 3050 graphics card. This is the company's first TUF Gaming product based on the RTX 3050, which was, until now, given the ASUS ROG Strix and DUAL OC custom treatment. What's more interesting is its cooling solution, which appears to be the first TUF Gaming graphics card with RGB LED lighting—a change from the functional, industrial look of TUF Gaming graphics cards.

This is also the smallest iteration of the TUF Gaming cooling solution the company debuted with the RTX 30-series "Ampere," and features a dual-fan setup (compared to triple-fan on every other TUF Gaming product from this generation). The card comes with a strip of RGB LEDs lined along the top of the card, at the edge of the backplate. It's being reported that this RTX 3050 card is based on the smaller "GA107" silicon, instead of "GA106," and hence comes with a lower typical board power than GA106-based RTX 3050 cards, with no difference in performance.

When NVIDIA launched the GeForce RTX 3050 "Ampere" based on the "GA106" silicon with specifications that could be fulfilled with the smaller "GA107," we knew that the company could eventually start making RTX 3050 boards with the smaller chip, and they did. Igor's Lab reports that RTX 3050 cards based on GA107 come with a typical board power of 115 W, which is about 11 percent lower than that of the GA106-based cards (130 W).

There's no difference in specifications between the two cards. Both feature 2,560 CUDA cores across 20 streaming multiprocessors, 80 Tensor cores, 20 RT cores, and a 128-bit wide GDDR6 memory interface, holding 8 GB of memory that ticks at 14 Gbps data-rate (224 GB/s bandwidth). The GA106 and GA107 ASICs share a common fiberglass substrate, and hence are pin-compatible for the convenience of board partners, with the latter having a smaller die, so any cooling solution designed for the launch-day RTX 3050 should work perfectly fine with those based on GA107.

The recently announced NVIDIA GeForce RTX 2050, MX570, and MX550 Ampere graphics cards have recently been benchmarked in 3DMark TimeSpy. The RTX 2050 and MX570 both feature the Ampere GA107 GPU with 2048 CUDA cores paired with 4 GB and 2 GB of 64-bit GDDR6 memory respectively. The MX550 uses the TU117 Turing GPU with 1024 CUDA cores running at 1320 MHz paired with 2 GB of 64-bit GDDR6 12 Gbps memory. The RTX 2050 and MX570 performed similarly in the 3DMark TimeSpy benchmark achieving a graphics score of 3369 while the MX550 scores 2510 points. These new laptop graphics cards will be officially launching in Spring 2022.

The NVIDIA MX550 has allegedly surfaced as part of a new Lenovo laptop in a Geekbench listing paired with an Intel Core i7-1260P 12 core, 16 thread processor. The card is described as a "Graphics Device" in the Geekbench listing however according to ITHome this is actually the upcoming MX550 entry-level mobile graphics card. The card is supposedly based on the Ampere GA107 GPU with 16 Compute Units and 128 CUDA cores paired with 2 GB of GDDR6 memory. The MX550 is the successor to the MX450 launched in August 2020 and should offer a roughly 15% performance increase according to the Geekbench OpenCL score. We have limited information on the availability of the card or the remainder of the MX500 series except that NVIDIA may officially announce them sometime early next year.

NVIDIA has today launched the latest addition to its data-centric graphics card lineup, called A2 Tensor Core GPU. The company envisions the A2 Tensor Core GPU as an entry point of accelerators that power machine learning and artificial intelligence at the edge. It is based on Ampere architecture and built on Samsung's 8 nm node. The GPU has GA107 GPU with 1280 CUDA cores enabled, where the full GA107 has 3072 cores. This GPU has only 1280 CUDA cores because it is configured as a low-power, low-profile body with a configurable TBP (total board power) of 40-60 Watts, depending on the customer use case.

It directly replaced the previous generation T4 accelerator, an edge device, and promises to bring 20-30% higher performance in the same power envelope. As far as memory, it has 16 GB of GDDR6 memory running on a 128-bit bus and 200 GB/s memory bandwidth. The GPU core clocks at 1440 MHz base and 1770 MHz boost frequency, which outputs 4.5 TeraFLOPs of FP32 compute. A2 represents a significant upgrade over the previous T4 because it offers a 60% better price to performance ratio and 10% better power efficiency than the last generation. Overall, this release represents an excellent upgrade for customers that need basic AI processing at the edge, and no, gaming is not supported on these as video output is disabled.