Nvidia launched three new GPUs last month, part of an overhaul of the RTX 40 series designed to improve the value of the company’s $600 and up graphics cards.
But today, the company is quietly doing something it hasn’t done in more than four years: launching a sub-$200 graphics card. As spotted by TechPowerUp, Nvidia partners like Gigabyte have begun officially announcing a 6GB version of the old RTX 3050 graphics card, albeit with less memory and memory bandwidth, fewer CUDA cores, and lower power requirements.
The announcement comes just days after retail listings leaked, which generally indicate an MSRP of around $179 for the new-old card. This would make it the first sub-$200 graphics card launch from Nvidia since the GeForce GTX 1650 Super debuted in late 2019, a four-year gap caused in part by a cryptocurrency- and pandemic-induced GPU shortage that has lasted from Late to mid 2020. -Late 2022.
|RTX 3050 6GB
|RTX 3050 8GB
|GTX 1650 Super
|RTX 2060 6GB
|RTX 3060 12GB
|2048 or 2304?
|Boost the clock
|Display the memory bus
|4 GB GDDR6
|12 GB GDDR6
We didn’t like the original 8GB version of the 3050 — “weird,” “overpriced” and “could have been worse,” we wrote about it during the depths of the GPU shortage in early 2022 — and the 6GB version was cut down to Beyond that. 6GB of memory connected to a narrow 96-bit memory bus. While reports vary on the exact number of CUDA cores we can expect — TechPowerUp and Tom’s Hardware say 2,048, while Gigabyte’s 6GB 3050 product pages list 2,304 — it’s clear there are fewer cores than the original RTX 3050, and the speed Her watch is lower than her boot.
These specifications should make the card suitable for 1080p gaming at medium to high settings, depending on the game. It should also be well-suited to small-format systems — one Gigabyte version is a compact card suitable for many desktops — and the 70W power requirement should mean the cards can draw all the power they need from a PCI Express slot, without needing a connector External energy.
As a shortened version of a 2-year-old card based on a 3.5-year-old last-gen GPU architecture, the RTX 3050 isn’t very exciting. But it gets even more interesting when you consider that Nvidia’s partners are currently selling the old, non-Super version of the GTX 1650 for about the same price. It’s hard to predict how much the narrower memory bus will affect the performance of the 6GB 3050, but compared to the 1650, it has a much larger number of newer CUDA cores, ray tracing support, another 2GB of RAM, GDDR6 instead of GDDR5, and RAM support. Nvidia’s DLSS upgrade (though not DLSS framework creation, which remains exclusive to the 40 series).
The new card also complicates one of AMD’s selling points for the new Ryzen 8000G processors, which includes reasonably capable 1080p integrated GPUs. AMD compared the Ryzen 7 8700G’s $329 cost favorably with that of a Core i5 CPU and GTX 1650 GPU, which offer similar performance for more money. But the RTX 3050 should decisively outperform the 8700G, and AMD’s pricing argument was already being undermined by the additional cost of Socket AM5 and DDR5 motherboards.
Nice as it is to see at least some As the entry-level GPU market goes, we’re still a long way from where we were in the mid-to-late 2010s, when sub-$200 cards like the GTX 1050 Ti and 1650 launched shortly after other cards from the same series launched and used newer GPU architectures. Graphics processing available at the time. There is a laptop GPU in the RTX 4050 series, but a desktop version seems highly unlikely at this point — let alone a desktop version priced at $200 or less. But the late and uninspiring improvement is an improvement nonetheless.