Tag:

AMD

AMD claims ‘regional market demand’ is why we’ve seen few 8 GB RX 9060 XT reviews, implying low VRAM isn’t really for the West

by admin June 5, 2025

Budget GPU launches over the last couple of months should have been received with mainstream excitement, but this has been hampered not just by real-world pricing issues but also by VRAM. Gamers haven’t seemed particularly happy with 8 GB options, especially when first Nvidia and then AMD seemed to keep them away from the bulk of popular reviewers. And on this point, AMD claims to have an explanation.

Veritable PC hardware demigod Linus Tech Tips (LTT) has shared what is implied to be a communication from AMD with the company stating that the lack of 8 GB AMD Radeon RX 9060 XT graphics cards given to popular reviewers is due to “regional market demand.” This is similar to what Nvidia has told us before.

Specifically, AMD says: “As for the 8 GB models, AMD has enabled global reviews of both 16 GB and 8 GB models of the Radeon RX 9060 XT based on regional market demand. So in short, yes, there are some other global publications that are receiving 8 GB models for testing.”

We ourselves received just a 16 GB version of the new graphics card which launched yesterday, and it looks like most others received the same, with only a couple of reviewers being given an 8 GB version (Uniko’s Hardware, for instance).

The concern is that AMD could be trying to limit review coverage of the 8 GB version because it knows it will be slated by the western media as not good enough for gaming in modern titles at higher resolutions than 1080p. As long as initial reviews are for the 16 GB version, positive opinion might be cemented (so the thinking goes).

This Was Supposed to be a Happy Day – YouTube

Watch On

8 GB can get you by at 1080p, and it can do less asset-rich games at higher resolutions, but you’ll need more VRAM than that to make the most of some AAA games even at lower resolutions and even some non-AAA games at higher resolutions.

This is the same criticism that many pitched at Nvidia when it launched the RTX 5060 Ti and seemed to do the same as AMD has now done, limiting the number of 8 GB versions that go out for review. Then the RTX 5060 launched and that doesn’t have a 16 GB version at all, nor did Nvidia seem keen on letting us review that one ahead of release.

Though it’s worth noting the RTX 4060 Ti launched in 8 GB form first and 16 GB later, following consumer pressure to launch the higher VRAM version and despite Nvidia’s protestations. Also AMD launched the 8 GB RX 7600 first last generation, followed by the 16 GB RX 7600 XT.

Chief architect of gaming solutions and gaming marketing at AMD, Frank Azor, has been defending the existence of 8 GB GPUs.

(Image credit: Future)

AMD’s response to LTT implies that none of this is AMD trying to squash 8 GB reviews but is instead a simple matter of efficient distribution and marketing. If western markets don’t tend to go for the 8 GB versions, and if the media responds negatively to them, then why ship samples out for review there? Companies don’t have to ship review samples that they don’t think will be beneficial from a business standpoint, after all.

This might be true, but it only shines a light on the question of why the western market might not have much time for an 8 GB version of the RX 9060 XT. And this, arguably, comes down to pricing. Moving down from 16 GB to 8 GB won’t nerf performance massively in most games at 1080p or even 1440p, but the difference isn’t inconsequential, either. And of course there’s the question of longevity, too. Given this, it’s reasonable that many might want more than a mere $50 saving for the 8 GB version compared to the 16 GB one.

Though even at the lower price, would some still be critical of an 8 GB card? You can’t please everyone…

It’s also worth noting that based on what Nvidia has told us, it shared this view. In a previous discussion, Nvidia had told us that the RTX 5060 Ti 8 GB was a good decision for markets outside the West; it’s for a global audience.

None of this detracts from the prowess of the 16 GB versions such as the one we tested, of course. The RX 9060 XT is a great card for its $349 MSRP. That’s $80 cheaper than the RTX 5060 Ti 16 GB and it outpaces the latter by 14–23% at both 1080p and 1440p depending on whether you use upscaling and frame gen.

All of this price talk could, of course, be rendered pointless over the coming weeks and months depending on what real-world prices are like outside of the mythical lands of MSRP. We’ll have to wait and see.

Source link

June 5, 2025 0 comments

Gaming Gear

AMD Radeon RX 9060 XT graphics card roundup: Every announced card from every AIB partner

by admin June 3, 2025

The RX 9060 XT launches on June 5th but that has not stopped AMD’s partners from showing off their respective versions beforehand. Asus, Sapphire, XFX, ASRock and Gigabyte have released listings of 8GB and 16GB versions of the RX 9060 XT boasting triple-fan and dual-fan cooling solutions. We’ve put together a list of all partner models from the aforementioned brands below.

AMD’s RX 9060 XT is its latest generation mid-range GPU, aimed at competing against GPUs like the all-new RTX 5060. The new GPU boasts 2,048 shader cores, 32 CUs, a 128-bit interface, and runs on AMD’s latest RDNA 4 architecture. Essentially, the RX 9060 XT is an RX 9070 XT that has been cut in half.

AMD is offering two memory capacities for the RX 9060 XT, 8GB and 16GB, with the 8GB variant featuring a 10W lower power rating than the 16GB model (at least for the reference specs). AMD claims the 8GB variant will be “good enough” for 1080p gamers, while the 16GB counterpart is geared towards higher resolutions.

You may like

MSRP for the 8GB model is $299, and the 16GB model $349. Of course, AIB partner model pricing will vary and be more expensive than MSRP, depending on the model.

Sapphire

Image 1 of 5

(Image credit: Sapphire)(Image credit: Sapphire)(Image credit: Sapphire)(Image credit: Sapphire)(Image credit: Sapphire)

Sapphire — one of the most recognized AMD partners, has four RX 9060 XT models in its arsenal consisting of one Nitro+ variant, one Pure variant and two Pulse models.

The Nitro+ model is Sapphire’s flagship version of the RX 9060 XT, available exclusively in 16GB capacity. It is one of the most exotic 9060 XT cards featuring a fat triple-slot cooler design with a massive grille on the side that serves both aesthetical appeal and functionality. The side area is so large that Sapphire was able to fit a RGB bar on the bottom, while providing more than enough room for air to travel out the side simultaneously.

The Nitro+ variant comes with a variety of features including fuse protection, fan quick disconnects (for easy fan replacements), an internal ARGB header, and FrameDefense; a special architecture that provides improved graphics card durability and rigidity. The Nitro+ model also comes with a Honeywell PTM7950 thermal pad instead of thermal paste, allowing the card to function for years without the effects of thermal paste degradation (or “pump out”).

One feature that is missing from the RX 9060 XT variant is a hidden 12V-2×6 power connector; a feature that the RX 9070 series counterparts came with. Instead, Sapphire opted to put the RX 9060 XT’s 8-pin power connector on the side where it normally sits on most graphics cards

The Pure variant is technically Sapphire’s mid-range offering, featuring a white finish and a dual-fan cooler design, though in the RX 9060 XT’s case, it is essentially a white version of the Pulse model.

The Pulse models are Sapphire’s entry-level solutions featuring a black finish with red accents. Both the Pure and Pulse models share many of the Nitro+’s features including the Honeywell PTM7950 thermal pad and FrameDefense. The main advantage of the Pure and Pulse models are their smaller 2.3 slot form factor and shorter footprint afforded to them by their more compact dual-fan cooler designs.

XFX

Image 1 of 5

(Image credit: XFX)(Image credit: XFX)(Image credit: XFX)(Image credit: XFX)(Image credit: XFX)

Contrary to Gigabyte, XFX has a plethora of RX 9060 XT models with a whopping 12 models in total comprised of triple-fan and dual-fan cooler options in both 8GB and 16GB trims. In typical XFX fashion, the AIB partner barely shows any features of their GPUs beyond core specs.

The Mercury class is XFX’s flagship lineup, consisting of two identical 16GB triple-fan models (with the only difference noticeable being each card’s physical model name). The Mercy cards sport an aggressive-looking triple-fan design with a sharp angular shroud and a silver color scheme.

The Swift class represents XFX’s mainstream lineup of RX 9060 XT graphics cards, including triple and dual fan cooler options. The triple fan options are comprised of five models, three featuring 16GB trims and the other 8GB trims. Out of the five models, two are white and four are black. The triple-fan cards come with a boxy shroud with either a pure white or pure black color scheme, along with an XFX logo on the right side that is illuminated.

The dual-fan options are comprised of five models as well, with four black models, and two white models. Three of the cards are 8GB variants while the other two are 16GB. These smaller cards carry on the same aesthetic and shroud design as their triple-fan counterparts but forgo illumination on the XFX logo on the side.

Despite having an impressive number of variants, none are factory overclocked.

Asus

Image 1 of 3

(Image credit: Asus)(Image credit: Asus)(Image credit: Asus)

Asus is providing four versions of the RX 9060 XT: one Dual model, two Prime variants, and a single TUF Gaming SKU. Memory capacities are split based on model hierarchy; the Dual gets the 8GB RX 9060 XT trim, the Prime lineup gets both 8GB and 16GB trims, and the TUF Gaming gets the 16GB version.

The TUF Gaming card represents Asus’ flagship graphics card for the RX 9060 XT series, featuring a rugged militaristic design with aggressive edges, and a gunmetal color theme with silver accents. The card is a 2.5-slot design, featuring a triple-fan cooling solution with “Military-Grade Components” such as TUF-branded chokes and MOSFETS.

The Prime cards feature the same 2.5-slot form factor and a similar triple-fan cooler design as the TUF Gaming model. Most notably, the card’s aesthetic is radically different, boasting a less aggressive black finish with a very round shroud on the edges. The Prime models boast a look that works in both non-gaming and gaming-focused builds.

The Dual model represents Asus’ entry-level and only dual-fan cooling solution for its RX 9060 XT graphics card lineup. The card has the same 2.5 slot design as its triple-fan counterparts but is much shorter thanks to its dual-fan cooler design. The card boasts a stealthy black color scheme and no RGB lighting.

Gigabyte

(Image credit: Gigabyte)

Gigabyte is only offering one RX 9060 XT model at this time, that being a RX 9060 XT Gaming sporting a triple-fan cooler design. Gigabyte is offering four versions of this specific model, an 8GB SKU, 16GB SKU and factory overclocked versions of both.

With other GPUs, Gigabyte’s Gaming series represents its mid-range solution usually sandwiched between the Windforce and Eagle series below and the Aorus series above. The cooler is comprised of a triple-fan cooling solution with composite copper heat pipes and a copper plate connecting the GPU, VRAM and heatsink together. Power delivery is comprised of lower RDS(on) MOSFETs and ESR solid capacitors.

The card also uses Gigabyte’s “server-grade” thermal conductive gel that has been prone to leaking in the past, but does not affect reliability (the issue has also since been allegedly solved by Gigabyte). The exterior is largely minimalistic sporting a rugged-esque grey finish with minimal RGB lighting.

We have not heard if Gigabyte will be releasing other variants of the RX 9060 XT, but at least for now, the Gaming cards will be its sole RX 9060 XT model.

ASRock

Image 1 of 2

(Image credit: ASRock)(Image credit: ASRock)

ASRock has two RX 9060 XT models in total, a Steel Legend variant, which features a white triple-fan cooler design, and a Challenger model, which is its budget-friendly dual-fan scounterpart. All of ASRock’s RX 9060 XT GPUs are factory overclocked.

The Steel Legend currently serves as ASRock’s flagship model featuring two sub-models, an 8GB model and a 16GB model. The card comes with the Steel Legend’s traditional white color scheme with a white shroud accompanied by RGB illuminated fans and grey accents.

Cooling is comprised of a nickel-plated copper base and ultra-fit heat pipes sandwiched very close to each other near the contact point to maximize thermal efficiency. The card also uses high-density metal welding, which allegedly improves heat dissipation. Power delivery is comprised of a Dr. MOS integrated power stage solution and premium power chokes.

Similar to the Nitro+, the Steel Legend comes with an ARGB header internally, enabling the GPU to control dedicated ARGB equipment. This feature is particuarly useful on older motherboards that lack ARGB headers altogether.

The Challeger represents ASRock’s budget-friendly solution, and is the smallest of the two GPUs sporting a dual-fan cooler design. The card comes in a black finish with minimal RGB lighting and some grey accents for extra flair.

The card features the same high-density metal welding and ultra-fit heatpipes as the Steel Legend but trimmed down in a more compact cooling solution. Power delivery is comprised of a Dr.MOS power stages solution and premium 90A power chokes.

Source link

June 3, 2025 0 comments

Gaming Gear

ASRock acknowledges and explains dying AMD 9000-series chips in its motherboards, rolls out a BIOS fix

by admin May 28, 2025

ASRock answered me why Ryzen 9000 CPUs are dying on their Motherboards. – YouTube

Watch On

Among many other descriptors, we could arguably call the last year one of hardware being pushed to the point of failure—think Intel CPU crashes, melting RTX 50-series power cables, and dying AMD Ryzen 9000-series CPUs on certain motherboards. We already had explanations for the former two, and it now looks like we might have an explanation for the 9000-series deaths, too.

ASRock has apparently told Tech YouTuber Tech Yes City that these 9000-series fatalities were caused by PBO (Precision Boost Overdrive) being set too high. While the problems didn’t just seem to be occurring with ASRock boards, the majority did, so it’s relevant that ASRock is the company saying this.

As a reminder, we started hearing about these AMD Ryzen 9000-series CPU deaths, primarily on ASRock motherboards, early on in the year. At the time, ASRock said that reports of these deaths were “inconsistent” and issued a statement only about “boot issues and error codes,” not processor failures. A BIOS update to fix these “boot issues and error codes” was released.

You may like

Now, however, ASRock seems to be admitting there’s not only “inconsistency” to reports of CPU failures.

According to Tech Yes City, ASRock explains that the problem is with the amperage that the CPUs are being delivered by high-end ASRock boards. While the motherboard manufacturer says its EDC (Electrical Design Current) and TDC (Thermal Design Current) settings were within the range outlined by AMD, it claims the resulting amperage was too high for the CPUs and so it’s had to lower things somewhat.

Finally got answers to the asrock motherboard and 9000 series cpus dying situation. Everything I was told was here https://t.co/BRqVRJAP3mMay 26, 2025

PBO is a technology built into AMD processors that allows for automatic dynamic adjustment of power, voltage, and clock speed, based on temperature headroom and other such metrics. Just how much PBO pushes the chip can vary depending on motherboard current limits, and ASRock seems to be claiming that these limits were set too high in its high-end 9000-series motherboards despite the limits being within the range that AMD provided.

The solution, ASRock tells Tech Yes City, is to set these current limits to lower levels to match motherboards from other manufacturers such as MSI, Asus, and Gigabyte.

Tech Yes City had previously suggested that Ryzen CPUs were dying due to voltage spikes. ASRock motherboard amperage was actually lower than competitors’ in their testing, but it was spiking higher.

Whether this is AMD’s fault or ASRock’s is hard to say. On the one hand, if it’s true that ASRock was operating within the limits AMD had set out, it’s hard to put all the blame on the motherboard manufacturer. AMD has already said on the issue that it believes its chips are not dying, and in fact were no longer functioning due to memory incompatibility issues.

On the other hand, if other motherboard makers were already operating under lower limits that didn’t cause these problems, it must make us wonder whether ASRock could and should have known to do the same from the start.

Whatever the case, ASRock is apparently rolling out a BIOS update to fix the overly aggressive PBO limits. So, if you have a high-end 9000-series ASRock board, you should probably get downloading.

What isn’t yet clear is whether a processor that has already been used extensively within an affected motherboard will be permanently damaged or not. That was the case with Intel’s 13/14th Gen CPUs, which had to be replaced entirely. This matters not only for the short-term, but in the long-term. If any chip were to break down the line, outside of warranty, who is liable to replace it, AMD or ASRock? Is there an easy way to prove the damage, if any exists, to a chip from the motherboard?

Futher clarification on what this means for customers from both AMD and ASRock feels like an important next step.

Source link

May 28, 2025 0 comments

Product Reviews

‘Majority of gamers are still playing at 1080p’: AMD chief claims there’s still a place for 8GB GPUs, and he’s got a point

by admin May 25, 2025

Frank Azor, AMD’s Chief Architect of Gaming Solutions and Gaming Marketing, shared a post on X (formerly Twitter) last week in response to a gaming account questioning why AMD is still offering GPUs with 8GB of VRAM in 2025.

“Majority of gamers are still playing at 1080p and have no use for more than 8GB of memory,” Azor wrote. “Most played games [worldwide] are mostly esports games. We wouldn’t build it if there wasn’t a market for it. If 8GB isn’t right for you then there’s 16GB. Same GPU, no compromise, just memory options.”

Majority of gamers are still playing at 1080p and have no use for more than 8GB of memory. Most played games WW are mostly esports games. We wouldn’t build it if there wasn’t a market for it. If 8GB isn’t right for you then there’s 16GB. Same GPU, no compromise, just memory…May 22, 2025

There’s data to support Azor’s claims—according to the Steam Hardware Survey, over half of gamers (55.27%) are playing on 1080p monitors. The survey data also suggests plenty of people are holding out for more budget GPUs: One of the top five GPUs among Steam users in 2025 is still somehow the GTX 1650, which only has 4GB of VRAM. The number one GPU as of April is the RTX 4060 laptop version with 8GB of VRAM.

You may like

Limited VRAM has become a bit of a sore spot during the current, Nvidia-led GPU doldrums, with 8GB already proving an issue in the biggest, most graphically advanced games.

It’s even an open question whether the 5070’s 12GB of VRAM is sufficiently “future proof,” and the $379 MSRP of the 8GB 5060 Ti is a hard sell before you even get to the endemic price bloat from AIB partners.

But with a $299 MSRP, the 8GB RX 9060 XT is a different beast⁠—that is approaching a truly budget price. With so many gamers sticking to 1080p, and some of the biggest games in the world being less demanding “esports” picks like Marvel Rivals, or otherwise dark horse indie phenoms like Schedule One, REPO, and Palworld, the 9060 XT is shaping up to be an 8GB card that makes a good deal of sense, one on the more expensive side of “budget.”

Azor’s stance is in line with my personal gaming experience, too. I’ve been gaming on an 8GB Radeon RX 6600 for a couple of years now and have yet to run into performance issues, even running most of my games through a compatibility layer on Fedora Linux.

Most gamers don’t need a top-of-the-line GPU, and for some time now, it’s felt like all the buzz has been around Nvidia’s prohibitively expensive 30, 40, and 5090 cards, while the sub-$350, 1080p set has had to settle for hand-me-downs and mediocrities.

Those budget cards are not meant to be hooked up to high-end monitors, and the people who can afford a 1440p or 4K gaming monitor need to be realistic about the GPU they’ll need to power it.

There’s no harm in offering budget-oriented GPUs for those who need that option. It serves to keep PC gaming more accessible for those who want to play less demanding games like Fortnite or Minecraft, or the treasure trove of fantastic indie and retro games on PC.

If you’re not in that crowd, there’s always the 16GB version of the RX 9060 XT, along with plenty of other 12GB and 16GB cards. Now the only issue is making sure those juicy MSRPs are actually reflected in reality.

Source link

May 25, 2025 0 comments

Gaming Gear

AMD justifies the RX 9060 XT 8GB: “Majority of gamers are still playing at 1080p”

by admin May 24, 2025

AMD’s latest RX 9060 XT GPUs continue the saga of bifurcating mainstream options into different memory configurations for market segmentation. According to AMD’s Frank Azor, the 8GB flavor of the RX 9060 XT is designed to cater to the needs of the majority of gamers, who play at 1080p.

Gamers and developers have long bemoaned constrained memory capacities with modern GPUs. Even at 1080p, many demanding AAA titles can overwhelm 8GB GPUs, as confirmed by professional testing with cards like the RTX 5060 Ti 8GB. Despite sufficient raw horsepower, the constrained framebuffer often forces you to compromise on graphical fidelity or even resolution for a playable framerate. Nvidia’s RTX 5060 GPUs have been at the epicenter of this criticism, to the point where an older RTX 3060 12GB can outperform them in certain scenarios.

There were rumors that AMD might scrap the 8GB model, following the backlash faced by Nvidia. This proved to be inaccurate, as the product was likely too far in the pipeline to be axed. While the GPUs are still almost two weeks away from launch, enthusiasts have already begun raising concerns about the viability of the 8GB model. AMD’s Chief Architect of Gaming Solutions and Gaming Marketing, Frank Azor, stepped in to justify their rationale, stating these GPUs target the “majority of gamers,” who play at 1080p.

You may like

Based on the Steam Hardware Survey, this statement is largely accurate, as 1080p dominates with 55.27% of the market, followed by 1440p at 19.90%. Some would question: Does AMD’s product segmentation actively restrict more users to 1080p? Do you buy an 8GB GPU to play at 1080p, or do you play at 1080p because you have an 8GB GPU? The RTX 3070 Ti perfectly illustrates how a small framebuffer can handicap an otherwise capable GPU. The GB206 core powering the RTX 5060 Ti is, in fact, faster than the 3070 Ti, but how much of that potential power will never be realized due to insufficient memory allocation?

It wouldn’t surprise me if most of these models are earmarked for gaming cafes, where esports dominate and VRAM demands are low. However, the RX 9060 XT 8GB is quite awkwardly positioned as its raw power likely outstrips its VRAM capacity. An RX 9060 non-XT / RX 9050 8GB positioned in the $200-$250 range would’ve been a more suitable offering as an esports-only card. After all, the RX 9060 8GB is believed to be the successor to the RX 7600 8GB, which cost $269 at launch.

It will be interesting to see if AMD and board partners can manage to keep these GPUs at MSRP. The RX 9070 family hasn’t been the best indicator in this regard. We’ll have to wait until June 5th next month to find out.

Follow Tom’s Hardware on Google News to get our up-to-date news, analysis, and reviews in your feeds. Make sure to click the Follow button.

Source link

May 24, 2025 0 comments

AMD's and Pegatron's 128-GPU MI350X system

Product Reviews

Pegatron preps 1,177 PFLOP AI rack with 128 AMD MI350X GPUs

by admin May 23, 2025

Pegatron showcased a unique rack-scale solution based on 128 AMD’s next-generation Instinct MI350X accelerators designed for performance-demanding AI inference and training applications at Computex. The system precedes AMD’s in-house designed rack-scale solutions by a generation, so for Pegatron, this system will serve as a training vehicle to build rack-scale AMD Instinct MI450X-based IF64 and IF128 solutions that are about a year away.

The Pegatron AS501-4A1/AS500-4A1 rack-scale system relies on eight 5U compute trays, each packing one AMD EPYC 9005-series processor and four AMD Instinct MI350X AI and HPC accelerators for AI and HPC. The CPU and the accelerators are liquid-cooled to ensure maximum and predictable performance under high loads. The machine comes in a 51OU ORV3 form-factor, making it suitable for cloud datacenters relying on the OCP standards (read: Meta).

(Image credit: Tom’s Hardware)

The machine connects GPUs located in a different chassis using 400 GbE as AMD does not have proprietary switches for Infinity Fabric connections (in any case, the maximum scale-up world size of AMD’s Instinct is eight processors today). This contrasts with Nvidia’s GB200/GB300 NVL72 platform, which has 72 GPUs interconnected with the company’s ultra-fast NVLink connection. To that end, the Instinct MI350X system will barely match the GB200/GB300 NVL72 in terms of scalability.

You may like

The new machine will be used by OCP adopters for their immediate workloads and for learning how to better build AMD Instinct-based systems with loads of GPUs both from hardware and software ports of view. Pegatron’s machine is hard to overestimate for multiple reasons, main of which being setting the stage to challenge Nvidia’s dominance in rack-scale AI solutions.

(Image credit: Tom’s Hardware)

Given what we know about AMD’s Instinct MI350X, Pegatron’s 128-GPU rack-scale system based on these units offers up to a theoretical peak of 1,177 PFLOPS PFLOPs of FP4 compute for inference, assuming a near linear scalability. With each MI350X supporting up to 288GB of HBM3E, the system delivers 36.8TB of high-speed memory, enabling support for massive AI models that exceed the capacity of Nvidia’s current Blackwell-based GPUs.

(Image credit: Tom’s Hardware)

However, its reliance on Ethernet for GPU-to-GPU communication limits the system’s scalability. With a maximum scale-up domain of eight GPUs, the system is probably built for inference workloads or multi-instance training rather than tightly synchronized LLM training, where Nvidia’s NVL72 systems excel. Still, it serves as a high-performance, memory-rich solution today and a precursor toward AMD’s next-generation Instinct MI400-series solutions.

Follow Tom’s Hardware on Google News to get our up-to-date news, analysis, and reviews in your feeds. Make sure to click the Follow button.

Source link

May 23, 2025 0 comments

Product Reviews

AMD unveils Radeon RX 9060 XT at Computex 2025

by admin May 21, 2025

AMD has unveiled its 9060 XT GPU at Computex 2025. The midrange GPU will be the clear competitor to Nvidia’s 5060 Ti and goes toe-to-toe with it on almost every spec. Built on AMD’s 4-nanometer RDNA 4 silicon, the 9060 XT will pack 32 compute units, along with 64 dedicated AI accelerators and 32 ray-tracing cores.

AMD

Notably, the RX 9060 XT will ship in 8GB and 16GB GDDR6 versions, whereas Nvidia’s RTX 5060 Ti uses faster 28 Gb/s GDDR7, delivering roughly 40 percent more bandwidth (448 GB/s vs. approximately 322 GB/s) on the same 128-bit bus. We’ll have to wait for some side-by-side performance comparisons before drawing any strong conclusions from those specs.

AMD has listed the 9060 XT’s boost clock at speeds up to 3.13 GHz. The GPU boasts 821 TOPS for AI workloads and will draw a modest 150 to 182 watts from the board. The card will connect via PCIe 5.0 x16 and supports the now-standard DisplayPort 2.1a and HDMI 2.1b. Based on these initial specs, the 9060 XT should be a solid entry for games running at 1080p and a decent option for those at 1440p. Those wishing to play at 4K should still opt for the Radeon RX 9070 or 9070 XT.

Pricing and exact release timelines have not yet been announced.

Source link

May 21, 2025 0 comments

Gaming Gear

AMD launches Radeon AI Pro R9700 to challenge Nvidia’s AI market dominance

by admin May 21, 2025

AMD has been busy at Computex 2025, where the chipmaker unveiled the exciting Radeon RX 9060 XT and the Ryzen Threadripper 9000 series. To cap off its series of announcements, AMD is thrilled to introduce the Radeon AI Pro R9700, a PCIe 5.0 graphics card designed specifically for professional and workstation users.

RDNA 4 is an architecture geared towards gaming, but that doesn’t mean AMD can’t apply it to professional-grade graphics cards. For instance, RDNA 3 saw the mainstream Radeon RX 7000 series successfully coexisting with the Radeon Pro W7000 series. The same situation will occur with RDNA 4. AMD has already unveiled four RDNA 4-powered gaming graphics cards, yet the Radeon AI Pro R9700 is the first RDNA 4 professional graphics card to enter the market. The new workstation graphics card aims to replace the RDNA 3-powered Radeon Pro W7800, which has been faithfully catering to consumers since 2023.

The Radeon AI Pro R9700 utilizes the Navi 48 silicon. It’s currently the largest RDNA 4 silicon to date, with a die size of 357 mm² and home to 53.9 billion transistors. Navi 48 is also found in the Radeon RX 9070 series. It’s a substantially smaller silicon than the last-generation Navi 31 silicon, which is 529 mm² with 57.7 billion transistors. It’s nothing short of impressive that Navi 48 is roughly 33% smaller but still has 93% of the transistors of Navi 31.

You may like

Image 1 of 2

(Image credit: Future)(Image credit: Future)

Navi 48, a product of TSMC’s N4P (4nm) FinFET process node, adheres to a monolithic design. On the contrary, Navi 31 features an MCM (Multi-Chip Module) design, consisting of chiplets interconnected to a monolithic die. That’s the reason why Navi 31 is so enormous. The GCD (Graphics Complex Die) alone measures 304.35 mm², whereas each of the six MCDs (Memory Cache Die) is 37.52 mm².

With Navi 48, AMD returned to a monolithic die and, with N4P’s help, reduced the die size by 33%. Nonetheless, Navi 48 is up to 38% denser than Navi 31. The former has a density of 151 million transistors per mm², whereas the latter comes in at 109.1 million transistors per mm².

In terms of composition, the Navi 48 features 64 RDNA 4 Compute Units (CUs), which enable a maximum of 4,096 Streaming Processors (SPs). In contrast, the Navi 31 is equipped with 96 RDNA 3 CUs, for a total of 6,144 SPs. More CUs don’t necessarily mean more performance since RDNA 4 delivers considerable generation-over-generation performance uplift over RDNA 3.

AMD Radeon AI Pro R9700 Specifications

Swipe to scroll horizontally

Graphics Card

Radeon AI Pro R9700

Radeon Pro W7800

Architecture

Navi 48

Navi 31

Process Technology

TSMC N4P

TSMC N5 / N6

Transistors (Billion)

53.9

57.7

Die size (mm²)

357

529

SMs / CUs

GPU Shaders (ALUs)

4,096

4,480

Tensor / AI Cores

128

140

Ray Tracing Cores

Boost Clock (MHz)

2,525

VRAM Speed (Gbps)

VRAM (GB)

32 / 48

VRAM Bus Width

256-bit / 384-bit

L2 / Infinity Cache (MB)

64 ⁄ 96

Render Output Units

128

Texture Mapping Units

256

280

TFLOPS FP32 (Boost)

45.3

TFLOPS FP16 (INT4/FP4 TOPS)

90.5

Bandwidth (GB/s)

576 / 864

TBP (watts)

300

260 / 281

Launch Date

July 2025

April 2023

Launch Price

$2,499 / ?

AMD, being AMD as usual, didn’t reveal the Radeon AI Pro R9700’s entire specifications. However, the chipmaker did boast about the graphics card’s 128 AI accelerators, meaning it’s leveraging the full Navi 48 silicon. That means the Radeon AI Pro R9700 is rocking 4,096 SPs, 9% fewer than the Radeon Pro W7800. It also correlates to the former having 9% less AI accelerators. In the Radeon AI Pro R9700 ‘s defense, the CUs are RDNA 4, and the AI accelerators are second generation.

Regarding FP16 performance, the Radeon AI Pro R9700 peaks at 96 TFLOPS, 6% faster than the Radeon Pro W7800. AMD rates the graphics card with a 1,531 TOPS of AI performance.

AMD claims the Radeon AI Pro R9700 offers 2X improved performance over the Radeon Pro W7800 in DeepSeek R1 Distill Llama 8B. For some strange reason, AMD compared the Radeon AI Pro R9700 to the GeForce RTX 5080. Tested in a few large AI models, the Radeon AI Pro R9700 delivered up to 5X higher performance than the RTX 5080.

Image 1 of 9

(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)

The Radeon AI Pro R9700 is equipped with 32GB of GDDR6 memory. AMD has not disclosed the specifications regarding the speed of the memory chips or the width of the memory interface. Given that the Radeon Pro W7800 features 18 Gbps GDDR6, it is reasonable to conclude that the Radeon AI Pro R9700 should utilize memory chips with superior speed.

With 32GB of onboard memory, the Radeon AI Pro R9700 can tackle most AI models. It has the capacity of the Radeon Pro W7800, but not as much as the 48GB variant. The Radeon AI Pro R9700’s typical blower-type design will enable users to rock up to four of them inside a single system, such as AMD’s Ryzen Threadripper platform, which has good multi-GPU support. With four of them, users will have access to 128GB, more than enough for heavy models that exceed 100GB of VRAM usage.

Image 1 of 6

(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)

The Radeon AI Pro R9700 has a 300W TBP (Total Board Power). It’s 15% greater than the Radeon Pro W7800 32GB and 7% higher than the Radeon Pro W7800 48GB. Similar to most workstation-grade graphics cards, the Radeon AI Pro R9700 has the power connector at the rear. However, AMD has not indicated the type of power connector it employs, and it’s not visible in the provided renders. Considering the 300W rating, we would anticipate it to require two 8-pin PCIe power connectors. The Radeon AI Pro R9700 renders illustrate the graphics card featuring four DisplayPort outputs. Since it utilizes the RDNA 4 architecture, these outputs should conform to the 2.1a standard.

AMD has announced that the Radeon AI Pro R9700 will launch in July, but it has not revealed pricing details. In contrast, the Radeon Pro W7800 debuted at $2,499 two years ago and has maintained most of its value, currently priced at $2,399. We will soon learn the price of the Radeon AI Pro R9700 as its launch approaches in just a couple of months. AMD anticipates a healthy supply of the Radeon AI Pro R9700 from its partners, including ASRock, Asus, Gigabyte, PowerColor, Sapphire, XFX, and Yeston.

Follow Tom’s Hardware on Google News to get our up-to-date news, analysis, and reviews in your feeds. Make sure to click the Follow button.

Source link

May 21, 2025 0 comments

AMD's Jack Huynh on stage at Computex 2025 in front of an FSR 4 Redstone presentation

Product Reviews

AMD just gave us our first glimpse of FSR 4’s ‘Redstone’ update, with a host of machine learning-based improvements

by admin May 21, 2025

AMD just gave us our first look at a significant update to FSR 4, codenamed “Redstone.” The new update is due to arrive in the second half of this year, and looks like something of a catch-up phase to counter Nvidia’s recent efforts with DLSS.

Top of the list is Neural Radiance Caching, which is presumably the equivalent of Nvidia’s Neural Rendering tech. FS4 Redstone will also feature machine learning-enhanced ray regeneration, with some more machine learning magic (it’s not actually magic, I know) added to its Frame Generation tech, too.

(Image credit: AMD)

And a very shiny AMD-red car, of course. The news comes as a bit of a surprise as it didn’t turn up in our pre-briefing slides, but yours truly is sitting in Taipei right now at the press conference typing furiously on his laptop to catch you up.

You may like

More details to come, but enjoy some pretty pictures for now.

Image 1 of 3

(Image credit: AMD)(Image credit: AMD)(Image credit: AMD)

Source link

May 21, 2025 0 comments

Product Reviews

The ASUS ProArt A16 laptop gets you the latest from AMD and a giant screen

by admin May 20, 2025

ASUS is updating both its ProArt laptop and its Chromebooks with the latest internals for Computex 2025, and giving both families of laptops a more premium look, with new colors and tasteful finishes.

The ASUS ProArt A16 stands out as the most premium pick, with a black aluminum body, “stealth” hinge that bring the top half of the laptop nearly flush with the bottom and a smudge-resistant finish that should hopefully avoid fingerprints. Inside, ASUS is offering an AMD Ryzen AI 9 HX processor and a NVIDIA GeForce RTX 5070 Laptop GPU, both of which qualify the new ProArt as a Copilot+ PC. That means you’ll get access to Windows’ growing list of AI features, and ASUS is also including to apps — StoryCube and MuseTree — that can run generative AI models entirely locally. All packed into a laptop that’s around half-an-inch thick and has a 16-inch 4K OLED.

Asus

In terms of Chromebooks, ASUS is offering both normal models and Chromebook Plus versions that support Google’s AI tools. The ASUS Chromebook Plus CX34 has a 14-inch display that can fold flat and a 1080p webcam, alongside up to an Intel Core i5 and 8GB of LPDDR5 RAM. That’s enough to offer Gemini features locally, and you’ll get priority access to Gemini Advanced. The only real disadvantage is the giant ASUS logo that still looks awkward next to the similarly prominent Chromebook logo, and the limited color options: You can only pick between white or grey.

Asus

The ASUS Chromebook CX14 and CX15 come with up to an Intel Core N355 processor, put to 8GB of LPDDR5 RAM and up to 256GB of storage. If you’re curious about Google’s AI features, you can also purchase a Plus version of the CX14. Whether you get the 14-inch or 15-inch model, both come with a respectable selection of ports, including HDMI for connecting to external displays. Either size also gets a variety of color options: blue, and a sliver-y grey or a greenish-grey in a either a matte or textured finish.

Asus

The ASUS Chromebook CX34 is available now starting at $400 from both Walmart and Best Buy. Meanwhile, the rest of the above laptops won’t be available until Q2 2025. The ProArt A16 starts at $2,500 from ASUS’ online store and Best Buy. The Chromebook CX14 starts at $279 from Best Buy or Costco. The Chromebook Plus CX14 will be available for $429 from Best Buy. And finally the Chromebook CX15 starts at $220 and will be able to be purchased from Best Buy and Amazon.

Source link

May 20, 2025 0 comments