Skip to main content

AMD Navi graphic cards could offer RTX 2070-like performance for $250

AMD RX 590
Dan Baker/Digital Trends

AMD’s upcoming Navi graphics cards could dominate the midrange of the GPU industry if new rumors are to be believed. The first 7nm graphics cards from AMD could offer performance that outpaces its own Vega 64 flagship GPU and is comparable to that of Nvidia’s RTX 2070, with a price tag of just $250. Other cards in the range would be even cheaper, while still offering comparable performance to reasonably high-end GPUs.

Not much is known about AMD’s first new-graphics generation in what will be two years when they debut next year. Navi, as its currently code-named, is expected to be built upon a 7nm process, as AMD’s upcoming Zen 2 Ryzen CPUs will be. However, new rumors about Navi go much further than that and make drastic claims about performance, memory capacity, power requirements, and pricing. If true, they could shake up the midrange graphics industry dramatically.

These rumors come straight from AdoredTV  (skip to 20:50), which covers rumors about AMD’s Ryzen 3000 series CPUs in the same video. They’re far from confirmed and are inflammatory to say the least, so we’re not entirely sold on their accuracy. If true though, they suggest 2019 could be an even better year for AMD than the last couple have been.

Get your weekly teardown of the tech behind PC gaming
Check your inbox!

The rumors claim that there will be three new Navi graphics cards at CES 2019, all launched under the banner of Radeon RX 3000. While that could get a little confusing considering that AMD’s new Ryzen lineup will have similar numbering, it could be a simple case of trying to one-up Nvidia’s RTX 2000-series — something that AMD previously did with the launch of its X470 and B450 motherboards.

The first card will reportedly be named the RX 3080 and will be built on the Navi 10 GPU. It will sport 8GB of GDDR6, which backs up AMD’s road map that suggested Navi would use next-generation memory. Its TDP is reportedly just 150W, 35w lower than the RX 580. Performance-wise, we’re told this card will be as much as 15 percent faster than a Vega 64, with comparable performance to that of an RTX 2070.

Most importantly, though, it’s said to have a price tag of just $250. That’s half the cost of the cheapest 2070.

WCCFTech/AMD

The Radeon RX 3070 is said to be built on the Navi 12 GPU and will feature the same 8GB of GDDR6. Its TDP will be as low as 120w, with Vega 56 or GTX 1070-like performance. The RX 3060 will have comparable performance to an RX 580, with 4GB of GDDR6 at its disposal, but with a TDP of just 75w. Reportedly, that means it doesn’t require an additional power connector, which could make it amazing for small form-factor builds and passively cooled gaming systems.

None of this is confirmed in any official capacity and the pricing in particular seems too good to be true for consumers. However, AMD has typically offered far more bang for the buck at its midrange than at the top end, so it’s not impossible that it would focus its efforts on undercutting Nvidia, rather than trying to go head to head at the top end. This would also open up room for a much higher TDP Navi chip, or a dual-chip card that would be competitive with Nvidia’s best.

With Navi slated for a CES unveiling, we have less than a month to wait to learn how much truth there is to these rumors.

Jon Martindale
Jon Martindale is the Evergreen Coordinator for Computing, overseeing a team of writers addressing all the latest how to…
AMD’s new feature doubled my frame rate with a single click
RX 7900 XTX installed in a test bench.

AMD did exactly what I hoped it would do. Its Fluid Motion Frames feature, referred to as AFMF, originally promised a way to add frame generation to virtually any game. There was just one problem -- AFMF was bad. Really bad. Now, AMD is taking another swing at driver-level frame generation with AFMF 2, which works in any game for any of AMD's RX 6000 or RX 7000 graphics cards.

The new version takes a lot of cues from Lossless Scaling, a $7 Steam app that has catapulted in popularity over the past few months due to its ability to add frame generation to any game. AMD is now able to provide a similar level of quality, and with some clear upsides over Lossless Scaling if you own one of AMD's best graphics cards.
What's new here?

Read more
This could be the reason you upgrade your GPU
The RTX 4080 in a running test bench.

Now more than ever, the best graphics cards aren't defined by their raw performance alone -- they're defined by their features. Nvidia has set the stage with DLSS, which now encompasses upscaling, frame generation, and a ray tracing denoiser, and AMD is hot on Nvidia's heels with FSR 3. But what will define the next generation of graphics cards?

It's no secret that features like DLSS 3 and FSR 3 are a key factor when buying a graphics card in 2024, and I suspect AMD and Nvidia are privy to that trend. We already have a taste of what could come in the next generation of GPUs from Nvidia, AMD, and even Intel, and it could make a big difference in PC gaming. It's called neural texture compression.
Let's start with texture compression

Read more
AMD just revealed a game-changing feature for your graphics card
AMD logo on the RX 7800 XT graphics card.

AMD is set to reveal a research paper about its technique for neural texture block compression at the Eurographics Symposium on Rendering (EGSR) next week. It sounds like some technobabble, but the idea behind neural compression is pretty simple. AMD says it's using a neural network to compress the massive textures in games, which cuts down on both the download size of a game and its demands on your graphics card.

We've heard about similar tech before. Nvidia introduced a paper on Neural Texture Compression last year, and Intel followed up with a paper of its own that proposed an AI-driven level of detail (LoD) technique that could make models look more realistic from farther away. Nvidia's claims about Neural Texture Compression are particularly impressive, with the paper asserting that the technique can store 16 times the data in the same amount of space as traditional block-based compression.

Read more