Monday, May 11th 2026
AMD Radeon 9050 Leaks With 8 GB VRAM, More Stream Processors Than 9060
It seems as though AMD's Radeon RX 9000-series GPU family may finally be getting a true entry-level variant. According to a recent report by VideoCardz citing a source inside one of AMD's AIB partners, AMD will soon announce the AMD Radeon RX 9050 with 8 GB of GDDR6 VRAM and a down-clocked version of AMD's Navi 44 GPU also used in the RX 9060. AMD has not yet revealed any details about the potential upcoming GPU, but there is a spec sheet divulging some of the details of the GPU, including a higher core count than the RX 9060. The card is expected to require a minimum 450 W PSU, suggesting reasonably low power draw, although likely not low enough to power off the PCIe slot alone.
The aforementioned spec sheet lists a Game clock of 1920 MHz and a Boost clock of up to 2600 MHz for the RX 9050, although, notably, the actual stream processor count is up from 1792 on the RX 9060 to 2048 on the 9050. It's entirely possible that we will see the GPU modding community come up with some way to hack a higher clock speed onto the 9050 via something like a 9060 XT vBIOS or some similar trick, but until then it's entirely likely that performance will be lower than the 9060, because the clock speeds are slower on the 9050—13% lower Boost clocks and 20% slower Game clocks. The reports also note that the specifications are preliminary, so it may be the case that some of the stream processors will be disabled to put the 9050 below the 9060. This non-finalized spec means we are also unlikely to see the Radeon RX 9050 launch anytime soon. The spec sheet also lists a PCIe 5 ×16 bus width and an HDMI 2.1b and dual DisplayPort 2.1a ports.
Source:
VideoCardz
The aforementioned spec sheet lists a Game clock of 1920 MHz and a Boost clock of up to 2600 MHz for the RX 9050, although, notably, the actual stream processor count is up from 1792 on the RX 9060 to 2048 on the 9050. It's entirely possible that we will see the GPU modding community come up with some way to hack a higher clock speed onto the 9050 via something like a 9060 XT vBIOS or some similar trick, but until then it's entirely likely that performance will be lower than the 9060, because the clock speeds are slower on the 9050—13% lower Boost clocks and 20% slower Game clocks. The reports also note that the specifications are preliminary, so it may be the case that some of the stream processors will be disabled to put the 9050 below the 9060. This non-finalized spec means we are also unlikely to see the Radeon RX 9050 launch anytime soon. The spec sheet also lists a PCIe 5 ×16 bus width and an HDMI 2.1b and dual DisplayPort 2.1a ports.
78 Comments on AMD Radeon 9050 Leaks With 8 GB VRAM, More Stream Processors Than 9060
the bus is there to give tasks and data to the gpu. speed of the dram on the gpu also have an impact.
-- use a browswer with lots of adblockers as this url is infected by annoying ads:
www.pcgameshardware.de/3DMark-Software-122260/Specials/Punkte-Tabelle-Time-Spy-Benchmark-1357989/2/
that page shows "3DMark Time Spy & TimeSpy Extreme" an interesting overview ofer graphic cards.
i state, that I need a certain performance tier. the graph there could be use to determine the basic level of a graphic card.
too bad i do not have such a chart which also includes the ryzen 7600x cpu graphcs, ryzen 4650u graphics and the older intel graphics and newer intel cpu graphics.
The next upgrade after my 19k points for my radeon 7800xt is only the nvidia 5090. anything else performs the same. not worth to consider anything else, not even the 5080.
We are stuck too long in the 19k segment
To play that I'm considering upgrading my graphics card and currently only have two options: get a bigger case (and figure out where I could squeeze it in under the TV) or switch to an NVidia card.
I would be much happier with a low profile RX 9050 if it was available (or the rumoured RX 9060 XT low profile by Vastarmor being available in the West...although that doesn't seem to exist beyond a few articles in January).
The "efficient" die strategy doesn't work. It's also a big part of why Intel has such low marketshare. They are playing in the bottom end of the market. In addition to what you talked about the manufacturer with the top card gets to decide how to drive the market. That's why a more expensive slower Nvidia card sells more than faster and cheaper AMD card, because it has mindshare.
In sports #1 player gets to be rich. The #2, the guy right behind him, earns barely more money than an average wage earner.
5080 is a pointless card offering no meaningful benefits over 5070 Ti and being slow compared to 5090.
Even Nvidia themselves are not in a hurry to beat it with anything of better value or speed.
Besides historical examples show that it doesn't matter how fast AMD is.
AMD could release a 5090 beating card tomorrow for half the 5090 price and people would still buy the 5090.
Because of mindshare, features etc. Or just straight up fanboyism which wee see plenty in this forum too.I think their R&D costs are well covered with the console deals.Because it had 3 year head start.
Because it's AI people and not gamers buying a 24GB card.Excluding AMD iGPU's does not change the overall percentages nearly as much as you want to believe.
Or are you forgetting that many percentages feeding into that 73% on Nvidia side also include their very popular mobile GPU's?
If we exclude both AMD iGPU's and Nvidia mGPU's then the overall percentages remain roughly the same in terms of dGPU's.
RX 9060 has same shader count but with higher clocks on a more advanced process node too. Why does it consume 2.5x the power?
This 8GB VRAM 9050? Who will this serve, I wonder, because nowadays 8GB isn't enough?Probably because AMD is silicon scavenging. Hardware harvesting defective or low-performing chips.
It's better to see if they can sell these for a profit than trash them in the garbage bin, I suppose.
Yeah, everyone and their grandma needs that.
Also that DLSS 5 thing. The runtime AI slop is priceless... :D
The specs make it strictly better than a Radeon 9060. More cores, higher base clock, same VRAM, same bus, same rated GDDR6 speed. The boost clocks are lower, but boost clocks on paper are as irrelevant as boost clocks IRL - they depend entirely on power limit, silicon lottery, and cooling headroom.
AMD marketing never misses an opportunity to do something utterly ass-backwards, so here we go again.
Better to have all 16 lanes available - especially when low VRAM and a relatively fast card.
Anyway, if this 9050 card costs $199, it wouldn't be bad I guess. I hope for 110 watts TDP.I agree that RTX 5060 Ti 16GB ought to cost $50-70 less than it costs, but I disagree it's a bad card overall. Uses a bit too much energy, but performance is very decent and VRAM is also very decent.
AI accelerators are selling for more profit per unit, most likely, and making a bigger RDNA4 configuration would take budget that they might as well spend on RDNA5
Most cards can run at half to 1/3 the wattage and still deliver decent performance. Not maximized for the silicon footprint, so some core performance is certainly wasted thanks to lower clocks, but the result is still good, especially for fitting into a slot-powered GPU.
Looking at the CPU/SoC side of things, Ryzen MCM has a relatively high power floor; meanwhile, the same uArch monolithic designs demonstrate incredible efficiency.
My point: Some 'chips' scale efficiency with lower clocks, better than others.