AMD Radeon RX 6000: Price, Release Date, Specs, and More
AMD Radeon RX 6000-series graphics cards are the best the company currently has to offer. The lineup currently includes the RX 6900 XT, 6800 XT, 6800, 6700 XT, and the RX 6600 XT, and they’re all powered by the RDNA 2 architecture inside the Xbox Series X and PlayStation 5. They also take on Nvidia’s Ampere GPUs across the most demanding games available today.
Outside of being more powerful than the RX 5000-series, RX 6000 graphics cards come with features like hardware-accelerated ray tracing and FidelityFX Super Resolution. They’ve also shown up in mobile configurations, and we expect to see them alongside APUs sometime next year.
As the sole focus on AMD’s Radeon division, there’s a lot of innovation happening with RX 6000 graphics cards. Here’s everything you need to know about them, including their pricing and availability.
Price and availability
The RX 6800 and 6800 XT launched on November 18, 2020, for $579 and $649, respectively. The 6900 XT arrived slightly later on December 8 for $999. The 6700 XT arrived in 2021 on March 18 for $479, and the RX 6600 XT followed up on August 11 for $379.
Short of the RX 6700 XT and RX 6600 XT, every card uses a triple fan design. The 6700 XT uses a dual fan design instead. The top two cards, the 6900 XT and 6800 XT, take up 2.5 slots while the 6800, 6700 XT, and RX 6600 XT use a dual-slot design. It’s important to note that AMD didn’t release a reference model for the RX 6600 XT, so board partner designs all vary a bit.
Compared to Nvidia’s competing Ampere GPUs, the 6800 matches up against the RTX 3070 ($499) while the 6800 XT edges toward the 3080 ($699). Similarly, the 6900 XT is positioned as a competitor to the 3090 ($1,500) while the 6700 XT should perform slightly better than a 3060 Ti but worse than a 3070. The RX 6600 XT competes with the RTX 3060, though its price is closer to the RTX 3060 Ti.
The big issue is availability. Despite poking fun at Nvidia’s stock issues during the 6000-series announcement, AMD is experiencing issues of its own. The entire GPU market is in a frenzy in 2021. You won’t find any current-gen cards in stock for more than a few minutes, and even most last-gen options are sold out online. There are a number of reasons why — U.S. tariffs, manufacturing issues, crypto mining, and just good old scalping, to name a few — but the end result is the same: It’s hard getting a GPU right now.
And the street price doesn’t match MSRP. The 6800 and its XT variant are nearly twice their MSRP at retailers like Newegg, and the secondhand market is even worse. Things are starting to improve, thankfully, but cards are still much more expensive than their list prices.
Performance
RX 6600 XT | RX 6700 XT | RX 6800 | RX 6800 XT | RX 6900 XT | |
GPU | Navi 23 XT | Navi 22 XT | Navi 21 XL | Navi 21 XT | Navi 21 XTX |
Interface | PCIe 4.0 | PCIe 4.0 | PCIe 4.0 | PCIe 4.0 | PCIe 4.0 |
Stream processors | 2,048 | 2,560 | 3,840 | 4,608 | 5,120 |
Compute units | 32 | 40 | 60 | 72 | 80 |
RT accelerators | 32 | 40 | 60 | 72 | 80 |
Base clock | 1,968MHz | 2,321MHz | 1,700MHz | 1,825MHz | 1,825MHz |
Boost clock | 2,589MHz | 2,581MHz | 2,105MHz | 2,250MHz | 2,250MHz |
Memory | 8GB GDDR6 + 32MB Infinity Cache | 12GB GDDR6 + 96MB Infinity Cache | 16GB GDDR6 + 128MB Infinity Cache | 16GB GDDR6 + 128MB Infinity Cache | 16GB GDDR6 + 128MB Infinity Cache |
Memory speed | 2,000MHz | 2,000MHz | 2,000MHz | 2,000MHz | 2,000MHz |
Bandwidth | 256GBps | 384GBps | 512GBps | 512GBps | 512GBps |
Memory bus | 128-bit | 192-bit | 256-bit | 256-bit | 256-bit |
TDP | 160W | 230W | 250W | 300W | 300W |
Four of the five of the RX 6000 cards punch above their weight class, though they can struggle with visual features like ray tracing. You’re not giving up much with an AMD card in 2021, and in some games, Team Red actually wins the day. Unfortunately, the performance of these cards doesn’t really play into value given the ongoing GPU shortage.
The cheapest RX 6600 XT actually represents the worst value in the range. It’s about 10% slower than the RTX 3060 Ti on average based on our testing and only $20 cheaper. In 3DMark Time Spy, for example, the RX 6600 XT scored 9,644 while the RTX 3060 Ti scored 11,706.
The RX 6700 XT starts the range, and it’s meant to compete with the RTX 3070. Based on our testing, the 3070 was 13% faster in 3DMark Time Spy, though the 6700 XT beat out the 3070 in the older 3DMark Fire Strike. In real-world performance, the 6700 XT was able to hit 75 fps in Assassin’s Creed Valhalla at 1440p, gaining an edge over the RTX 3070.
Ray tracing is where the RX 6000 range starts to fall apart. In Fortnite, we averaged just 33 fps with low ray tracing effects and global illumination turned on at 1080p. FSR helps in these situations, though it’s not always available alongside ray tracing.
Without ray tracing, the flagship 6800 XT trails the RTX 3080 in some games at 1440p and 4K. There are some titles that favor AMD’s card, though, such as Borderlands 3 and Dirt 5. Rasterized performance for the 6800 XT is about equal to the 3080, and the difference in frame rates between the two is really splitting hairs. Synthetic benchmarks like 3DMark Fire Strike actually peg the 6800 XT as the more powerful card over the 3080.
Once again, the differences come in ray tracing. Based on testing at Forbes, the 3080 delivered 97 fps at 1440p in Shadow of the Tomb Raider with ray tracing turned on. The competing 6800 XT achieved only 77 fps with the same settings. Compare that to the rasterized performance and the difference is clear. The 3080 achieved 151 fps without ray tracing while the 6800 XT followed with 146 fps. That’s a negligible difference.
The RX 6900 XT is supposed to compete with the RTX 3090, but it occupies its own space in the market. At stock frequencies, it performs slightly above the RTX 3080. When overclocked, however, the RX 6900 XT can reach performance levels on par with the RTX 3090 at 4K. In fact, the RX 6900 XT holds the GPU overclocking world record.
A big reason why you can overclock RX 6000 cards so far is their unique Infinity Cache. RX 6000 cards utilize 128MB of an L3 cache to expand the effective bandwidth of the vRAM. Compared to just using faster memory — as Nvidia did with its RTX 3000 cards — Infinity Cache delivers vastly higher effective bandwidth with less power consumption. Combined with the 7nm manufacturing process — compared to 8nm with Nvidia — RX 6000 cards are able to hit insanely high clock speeds.
Thanks to the one-click Rage Mode on RX 6000 cards, you can see these clock speeds in action. Rage Mode automatically overclocks your graphics card, allowing you to squeeze some extra performance out of it without knowing how to overclock a graphics card.
The 6000-series cards hold up well against Nvidia’s best without ray tracing. Ray tracing still favors Nvidia, but that doesn’t downplay just how powerful AMD’s latest cards are. Upgrading from a 5700 XT to a 6800 XT, for example, can yield as much as a 100% uplift in performance.
RX 6000M and APUs
During its Computex 2021 keynote, AMD announced RX 6000M mobile graphics cards. Although they mirror their desktop counterparts in name, the designs are slightly different to accommodate laptops (similar to how Nvidia handles GPUs across desktop and mobile). Right now, there are three cards available — the RX 6800M, RX 6700M, and RX 6600M.
We had a chance to test the flagship RX 6800M. AMD claimed that it could beat the mobile RTX 3080 in games like Assassin’s Creed Valhalla and Resident Evil: Village, but the results are a little more complicated. The RX 6800M can indeed beat Nvidia’s best in games optimized for RDNA2, but it can struggle in certain configurations based on our testing.
Although we initially hoped to hear about Ryzen 5000 APUs with RDNA 2 cores in 2021, that’s looking less likely as time goes on. AMD announced two new Ryzen 5000 APUs during its Computex 2021 keynote, both of which still use the aging Vega graphics cores. For RDNA 2 APUs, we have to look to the future.
We expect to see RDNA 2 graphics on next-gen Ryzen 6000 APUs. These APUs will reportedly use the Zen 3+ or Zen 3 XT architecture, building on the existing design used in Ryzen 5000 APUs. They’re also rumored to feature up to 12 RDNA 2-powered compute units. That’s four more than the current Ryzen 5700G, which could mean up to a 50% increase in graphics performance.
Hopefully the performance increase will be even greater. Next-gen APUs will feature more compute units, but more than that, they’ll feature the far superior RDNA 2 architecture. As the same architecture inside RX 6000 graphics cards, we expect to see large gains from Ryzen 6000 APUs once AMD is ready to release them.
Ray tracing and FidelityFX features
With RDNA2, AMD now offers fully hardware-accelerated ray tracing, though it does it in a slightly different fashion to Nvidia. It doesn’t have dedicated RT cores like RTX 2000 and 3000 cards, but incorporates a ray accelerator into the standard Radeon compute units.
AMD also expanded its library of Fidelity FX features to work hand-in-hand with ray tracing compute and shader effects to bring better visual fidelity to games. Denoiser and variable rate shading algorithms help to adapt image quality based upon luminance and motion, AMD said, and a suite of compute-based effects are also available to developers.
One of those effects is FidelityFX Super Resolution (FSR). FSR is a supersampling technique that can increase performance without a significant loss in image quality. It works by feeding an algorithm with a low-resolution internal render. The algorithm then takes that information and expands the pixels into a larger grid, leading to what looks like a high-resolution image.
FSR was positioned as a feature to challenge Nvidia’s DLSS, but it’s clear now that it works quite differently. AMD opted for an open approach with FSR, allowing as many devices as possible to use the feature (including RX 6000 graphics cards and the Xbox Series X). DLSS, on the other hand, uses some secret A.I. sauce from Nvidia and requires the dedicated Tensor cores featured on RTX graphics cards.
And like rival Nvidia, AMD will also use Microsoft’s Direct Storage API to help reduce game load times.
Editors’ Recommendations