“The RTX 4080 12GB is a fantastic graphics card, but it’s not named correctly. Having two GPUs with the 4080 designation is confusing. So we hit the ‘start’ button on the 4080 12GB. The RTX 4080 16GB is incredible and set to delight gamers everywhere on November 16,” says Nvidia in a remarkable new blog post that effectively halts the upcoming launch of the much-contested version of the RTX 4000, hinting that it will be renamed when in after all, it is renamed – they emerge. RTX 4070 Ti anyone?
Revealed by Nvidia boss Jensen Huang on September 20, the RTX 4000 line of graphics hardware is based on the new Ada Lovelace architecture manufactured on TSMC’s 4nm process. The flagship GPU – the GeForce RTX 4090 – was released a few days ago and was praised for its huge generational leap over the existing flagships RTX 3000, RTX 3090 and RTX 3090 Ti. However, it’s fair to say that the same level of acclaim and anticipation wasn’t given to the RTX 4080, announced in two very different variants.
The table below reveals that the spec difference isn’t just about the amount of on-board VRAM: each RTX 4080 model is based on a completely different processor core, with wild variations in the amount of CUDA codes (computing power) and memory bandwidth. In fact, two very different graphics cards are sold under the same name at very different price points.
RTX 4090 24GB RTX 4080 16GB RTX 4080 12GB processor AD102 AD103 AD104 Transistors 76.3B 45.9B 35.8B Size of the matrix 608mm² 295mm. 320W 285W PSU Recommendation 850W 750W 700W PSU Cables 4x 8-pin 3x 8-pin 2x 8-pin Price $1499/£1649 $1199/£1269 $899/£949 Release Date 1 October 16 November 2022 Delayed Nvidia GeForce RTX 4090 – Digital Foundry’s video review.
Specs are one thing, but real-world performance is another. No one has been privy to the product, but Nvidia’s own benchmarks suggest that the difference between the RTX 3080 and RTX 4080 won’t be as large as the performance increase offered by the RTX 4090 over the RTX 3090. Based on figures provided by Nvidia itself Nvidia , the 12GB RTX 4080 delivered improvements on various levels over the RTX 3080, sometimes beating the 3090 Ti, sometimes not. There was a sense that while the value seemed reasonable over the RTX 3080 Ti and up, the RTX 3080’s $699 price tag seemed problematic for the $899 RTX 3080 12GB in a world where new GPU lineups typically offer more power for your money. The performance figures for the 16GB model look a little stronger – at least there is clear water between generations here, even if the price is still high.
There has been pressure on the RTX 4080 12GB on many fronts – pricing, naming, specs – leading to Nvidia’s decision to delay and possibly rebrand the product. With that in mind, delaying and renaming the RTX 4080 12GB is the best way forward for Nvidia, as it puts the focus back on the upcoming RTX 4080 16GB version, while the difficult price/performance questions of the 12GB model can be addressed further down the line .
In the meantime, we have a firm release date for the “one true” RTX 4080 – November 16th – but in the meantime, competition in the graphics space could heat up. AMD’s new RDNA 3 line of graphics products is due to be unveiled on November 3rd, with the Radeon team also benefiting from new process technology as well as a move to the chiplet technology that has served AMD so well in the CPU space (instead of one expensive chip, different parts of the design will be created from a collection of smaller, cheaper processors). Nvidia is a strong contender, but there’s clearly an opportunity for Team Red to make an impact here. We’ll be reviewing all new graphics products as and when they come out.
To view this content, please enable targeted cookies. Manage cookie settings
Add Comment