Nvidia’s Blackwell laptop graphics cards are inbound for early 2025 (hopefully), and we’ve just caught a leak about how much video memory (VRAM) they’ll supposedly run with.
This one’s from Moore’s Law is Dead (MLID), a regular leaker on YouTube (and one of the more reliable sources for GPU and CPU leaks in our experience).
MLID has the purported full details of the VRAM, and they run as follows. The flagship RTX 5090 will supposedly be keeping exactly the same configuration as the RTX 4090, which some folks will doubtless find disappointing. Meaning it’ll run with 16GB of VRAM and a 256-bit memory bus.
Where the better news theoretically comes in is with the next model down, presumably the RTX 5080 – or maybe we’ll call it the second tier Blackwell GPU (you’ll see why in a moment) – weighing in with the same loadout of 16GB of VRAM (and 256-bit bus). That’s a solid increase from the current RTX 4080 laptop GPU which has 12GB.
There’s a slight catch of sorts here, though. If you recall, the RTX 4080 mobile GPU used a lesser chip than the flagship – the AD104 chip, rather than AD103 in the RTX 4090. But with the RTX 5080, a recent rumor (again from MLID) contends that it’ll use GB203, just the same as the flagship 5090, meaning it’s potentially going to be a fair bit peppier (with that VRAM upgrade on top, too).
What this also means is that Nvidia might want to reflect that and call it the RTX 5080 Ti, rather than just the plain 5080.
And that could have knock-on effects with the rest of the range, as if that’s the plan, then the third tier GPU (RTX 4070 equivalent) might be the RTX 5080. But if the second tier Blackwell GPU is the RTX 5080, then the third tier will obviously be the RTX 5070.
You get the idea anyway, but whatever it’s named, this third tier GPU will supposedly have 12GB of VRAM, an increase on the 8GB seen on the RTX 4070.
Finally, with the fourth tier GPU – the RTX 5060 most likely, or perhaps RTX 5070 if Nvidia goes with the 5090 / 5080 Ti / 5080 naming scheme – will be left with 8GB of VRAM. (Cue a chorus of boos and hisses).
Analysis: Good, bad, and 8GB ugly
So, there’s some good and bad news here – though add seasoning, and plenty of it, remembering this is just talk from the grapevine.
On the more positive front, we could get a powerful RTX 5080 relative to the RTX 4080 – so much so that Nvidia might brand it an RTX 5080 Ti. Either way, top-end options could be bolstered, and it’s good to see whatever the third tier GPU ends up being having an increase of 4GB of video RAM (being upped from 8GB to 12GB).
The not-so-great chatter here is, of course, not increasing the VRAM of the flagship mobile GPU for Blackwell, and worse still, maintaining a configuration of 8GB with that fourth tier GPU (RTX 5060 most likely – or as mentioned this could even be the RTX 5070, perhaps).
For gaming moving forward – remember, these are next-gen GPUs that’ll be reigning for a couple of years, through until 2027 (at least) – those two VRAM loadouts are far from great, and the choice of 8GB lower down seems particularly shaky.
Assuming Nvidia does go this route, of course, and we should underline it may not happen at all – so it’s too early to start worrying overly about these prospects.
However, regarding the possible level of accuracy here, MLID says this info comes from some of his best sources. We’re talking folks who have come up with the goods with early pics of GPUs before now – properly connected Nvidia leakers, in short. Given that, MLID is putting a good deal of weight behind these forecasts.
As ever, let’s see if other leaks fall in line with MLID’s predictions. But if this is true, the very top and bottom of the Blackwell spectrum of GPUs for gaming laptops is in danger of disappointing. In theory, these mobile graphics cards should be pitching up fairly early in 2025, most likely with a March release, as per previous spillage.