rdna 4 returns AMD’s $299 Radeon RX 9060 XT brings 8GB or 16GB of RAM to fight the RTX 5060 New midrange RDNA 4 GPUs launch starting on June 5, just weeks after RTX 5060. Andrew Cunningham – May 20, 2025 11:00 pm | 15 AMD's Radeon RX 9060 XT series comes in both 8GB and 16GB variations. Credit: AMD AMD's Radeon RX 9060 XT series comes in both 8GB and 16GB variations. Credit: AMD Story text Size Small Standard Large Width * Standard Wide Links Standard Orange * Subscribers only   Learn more AMD's Radeon RX 9070 XT and RX 9070 were fairly well received when they were released in March, ably competing with Nvidia's RTX 5070 and RTX 5070 Ti for the same or a little less money. We were impressed by the cards' performance and power efficiency, even if they still have some of the same caveats as older Radeon cards (lack of DLSS upscaling and lower relative ray-tracing performance being two). Today AMD is formally expanding its family of RDNA 4 graphics cards with the Radeon RX 9060 XT, a GPU that will go up against Nvidia's RTX 5060 and RTX 5060 Ti GPUs. These GPUs have just half the compute units of the RX 9070 XT, but at $299 and $349 for 8GB and 16GB configurations, they ought to be decent options for 1080p or entry-level 1440p gaming PCs (with the eternal "if you can find them" caveat that comes with buying a GPU in 2025). AMD says the new GPUs will be available starting on June 5th from the typical range of partners—AMD released renders of a reference GPU design, but sometimes these are starting points that manufacturers can take or leave, rather than products AMD intends to manufacture and sell itself. Specs and speeds RX 9070 XT RX 9070 RX 9060 XT RX 7600 XT RX 7600 Compute units (Stream processors) 64 RDNA4 (4,096) 56 RDNA4 (3,584) 32 RDNA4 (2,048) 32 RDNA3 (2,048) 32 RDNA3 (2,048) Boost Clock 2,970 MHz 2,520 MHz 3,130 MHz 2,755 MHz 2,655 MHz Memory Bus Width 256-bit 256-bit ? 128-bit 128-bit Memory Bandwidth 650GB/s 650GB/s ?GB/s 288GB/s 288GB/s Memory size 16GB GDDR6 16GB GDDR6 8 or 16GB GDDR6 16GB GDDR6 8GB GDDR6 Total board power (TBP) 304 W 220 W 150 (8GB) or 160 W (16GB), up to 182 W 190 W 165 W Per usual, AMD has priced the cards competitively with Nvidia's offerings, but not so aggressively as to totally undercut the GeForce cards. The 8GB variant of the card is priced against Nvidia's $299 RTX 5060, where the 16GB version attempts to undercut the $429 RTX 5060 Ti. Adding more RAM won't improve performance across the board in all games, but it ought to improve things disproportionately at 1440p, and it seems like AAA games are bumping up their RAM requirements all the time. AMD didn't provide much by way of performance comparisons, but it's promising that the cards have the same number of compute units as AMD's last-generation RX 7600 series. AMD says that RDNA 4 compute units are much faster than those used for RDNA 3, particularly in games with ray-tracing effects enabled. This helped make the Radeon RX 9070 cards generally as fast or faster than the RX 7900 XTX and 7900 XT series, despite having around two-thirds as many compute units. Sticking with 32 CUs for the 9060 series isn't exciting on paper, but we should still see a respectable generation-over-generation performance bump. The RX 7600 series, by contrast, provided a pretty modest performance improvement compared to 2022's Radeon RX 6650 XT. Renders of AMD's reference card for the 9060 XT series. Renders of AMD's reference card for the 9060 XT series. No surprises here: it's a compact dual-fan design with a single 8-pin power connector. AMD No surprises here: it's a compact dual-fan design with a single 8-pin power connector. AMD Renders of AMD's reference card for the 9060 XT series. No surprises here: it's a compact dual-fan design with a single 8-pin power connector. AMD AMD says that the cards' total board power—the amount of power the entire graphics card, including the GPU itself, RAM, and other components—starts at 150 W for the 8GB card and 160 W for the 16GB card, with a maximum TBP of 182 W. That's a shade higher than but generally comparable to the RTX 5060 and 5060 Ti, and (depending on where actual performance ends up) quite a bit more efficient than the RX 7600 series. This partly comes down to a more efficient 4nm TSMC manufacturing process, a substantial upgrade from the 6nm process used for the 7600 series. It's unusual for a GPU maker to define a TBP range—more commonly we're just given a single default value. But this is in line with new settings we observed in our RX 9070 review; AMD officially supports a range of different user-selectable TBP numbers in its Catalyst driver package, and some GPU makers were shipping cards that used higher TBPs by default. Higher power limits can increase performance, though usually the performance increase is disproportionately small compared to the increase in power draw. These power limits should also generally mean that most 9060 XTs can be powered with a single 8-pin power connector, rather than using multiple connectors or the 12-pin 12VHPWR/12V-2x6 connector. Listing image: AMD Andrew Cunningham Senior Technology Reporter Andrew Cunningham Senior Technology Reporter Andrew is a Senior Technology Reporter at Ars Technica, with a focus on consumer tech including computer hardware and in-depth reviews of operating systems like Windows and macOS. Andrew lives in Philadelphia and co-hosts a weekly book podcast called Overdue. 15 Comments