Nvidia’s RTX 4080 graphics card could be a minimal significantly less beefy than has been previously rumored, which follows swiftly on the heels of news that the RTX 4070 may possibly be a peppier GPU than expected.
This contemporary Lovelace speculation yet again will come from Kopite7kimi, a frequent hardware leaker on Twitter who has been giving rumors at very a rate of late (while which is to be anticipated as the RTX 4000 vary nears its launch timeframe, with an envisioned debut in or all around October, assuming no delays).
I am not a chatterbox, but I have to make some updates. I hope you really don’t thoughts. a doable RTX 4080, PG136/139-SKU360Advert103-300-A19728FP32256bit 16G 21Gbps GDDR6Xtotal electricity ~420WTSE ~15000Now I have finished the newest update for 4090, 4080 and 4070.August 5, 2022
The idea is that the ‘possible’ RTX 4080 – a reminder that absolutely nothing is necessarily established in stone, even if this is Nvidia’s present thinking with the spec of the GPU – could run with nine,728 CUDA Cores, which is fewer than the previously rumored 10,240.
The leaker believes that the RTX 4080 will occur equipped with 16GB of GDDR6X (at 21Gbps), and a energy utilization of about 420W, all of which continues to be in line with what was floated beforehand – the only modify is that trimming down of the main depend at this place.
Assessment: Nvidia’s positioning of RTX 4000 products
The first thing to note right here is that this is not a major improve. Dropping down 512 CUDA Cores – which indicates minimizing the streaming multiprocessors on-board by four, from 80 to 76 – is not a enormous shift, but it does nonetheless symbolize a slight reduction in raw grunt for the GPU.
Let us bear in intellect that this is just a rumor, and the leak landscape around Lovelace is seemingly shifting very routinely these days – which may be a reflection of Nvidia tinkering with and adjusting relative specs as the firm moves in direction of a finalized bunch of solutions.
As mentioned at the outset, Kopite7kimi also recently introduced us news on the RTX 4070, with the clear concept for that GPU remaining to up its performance degree at this phase – to the spec that was previously rumored for the RTX 4070 Ti, in simple fact. A rather massive phase up, for absolutely sure. So, assuming this is all correct, what may possibly Nvidia’s reasoning be below?
Bringing down the CUDA Main rely of the RTX 4080 a bit, while critically beefing up the RTX 4070 – not just for CUDA Cores, but the loadout of VRAM as properly – means, of course ample, that the relative general performance of the RTX 4070 and RTX 4080 is theoretically being introduced much more intently in line.
With much less differentiation in between the two, and Nvidia’s xx80 product generally being a good chunk more high-priced than the far more mainstream xx70 card – the somewhat economical large-conclusion GPU, if you will – with Lovelace, are we likely to be looking at an RTX 4070 which is even extra in the sweet location for most purchasers?
Or to place it an additional way, if the RTX 4080 is not all that considerably more quickly, who will fork out for a person instead than a 4070? Unless of course inventory is an concern for the latter, of system that could occur into participate in, especially if it’s really well known.
Also, we have to have to bear in mind that CUDA Cores aren’t the entire tale for general performance, with quite a few other variables coming into play, like clock speeds. It’s in this article that there could be a clue in the RTX 4070 supposedly sticking with all over 300W for electricity use, whilst the RTX 4080 will purportedly hit 420W or thereabouts – this could stage to Nvidia seriously beefing up clock speeds (and consequently performance) with the better-finish GPU in comparison to the 4070.
Furthermore, Kopite7kimi has managed the preceding guestimate for a 3DMark TimeSpy Intense score for the RTX 4080 (close to 15,000), despite people CUDA Cores being shaved off, so interestingly ample, that could also counsel Nvidia might be pushing more durable with clocks in this article for the 4080. Even though the leaker doesn’t mention clock speeds exclusively.
Surely it does not make feeling to have the RTX 4080 as a rather unattractive proposition in contrast to the 4070 – a a lot larger electricity usage will not help possibly, in terms of forcing PSU updates, and strength expenses in common – so for now, we’ll think that if this rumor is legitimate, we simply cannot but see the whole picture of what Nvidia is striving to do with the positioning of Lovelace GPUs. Or that there’ll be one more rejigging of specs however to come…
Relative pricing could be a element here, way too – we have not heard a lot on that front from the rumor mill but, but we can’t imagine the RTX 4000 sequence will be pitched with affordability in brain. Notably not if Nvidia has a lot of excessive RTX 3000 stock to offer with, as the grapevine contends, and shifting all that overlaps with the Lovelace launch (which is probably only a couple of months absent now).
Regardless of what the scenario, you’d imagine Team Environmentally friendly would’ve learned from its faults in terms of the RTX 3080 having off on the mistaken foot, coming with only 10GB of VRAM in its first incarnation – an unpopular move compounded by the afterwards release of a 12GB variant. The latter was beefier not just in terms of the extra movie memory, leaving some purchasers of the first RTX 3080 with a critical case of regret.