One thing to sit up for: Rumors and leaks concerning Nvidia’s next-generation graphics chips proceed to movement as the corporate’s plans doubtless stay in flux. Though the RTX 50 sequence flagship product will virtually actually launch this 12 months, the standing of its companions stays unclear. In the meantime, the lineup of AI chips that follows is already taking form.
Established leaker @kopite7kimi lately claimed that Nvidia may start delivery the RTX 5080 earlier than the extra highly effective 5090. New GPU generations sometimes debut with the flagship product, so this technique can be considerably uncommon.
The projected launch dates of the upcoming RTX 50 sequence graphics playing cards, codenamed Blackwell, have lately fluctuated between late 2024 and early 2025. Most predictions place the 5090 and 5080 earlier than the tip of this 12 months, with mid-range and mainstream variants following in 2025. Nevertheless, YouTuber Moore’s Regulation is Lifeless up to date his data to recommend that solely the top-end GPU would launched in 2024, prompting Kopite to reply, stating that the 5080 ought to debut first.
It isn’t ture. RTX 5080 ought to be launched first.
– kopite7kimi (@kopite7kimi) Might 7, 2024
One potential cause for the switch-up is that the RTX 5080 may outperform essentially the most highly effective Nvidia GPU at present accessible – the 4090 – thus making it essentially the most potent graphics card available on the market till the 5090 begins delivery. Most stories point out that rival vendor AMD will introduce the RDNA 4 lineup this 12 months, however it should solely include mid-range merchandise. Nevertheless, sources lately knowledgeable Benchlife that the brand new Radeon sequence may very well be delayed till 2025. Intel plans to launch its first-ever enthusiast-class GPU in 2024, however there may be nonetheless no indication of the way it compares to Blackwell.
Benchlife additionally stories that coolers for the RTX 50 sequence are at present present process testing, revealing 4 designs ranging between 250w and 600w. Trial wattage rankings do not essentially mirror last merchandise, so prospects should not anticipate the 5090 to require wherever close to 600w.
As an illustration, early stories surrounding the 40 sequence sparked concern that its flagship may draw over 800W, however the 4090 ended up solely utilizing 450W. On the alternative finish of the size, the preliminary 250W exams for Blackwell might symbolize an RTX 5070 or 5070 Ti.
Wanting additional forward, analyst Ming-Chi Kuo stories that the successor to Nvidia’s Blackwell AI GPUs, codenamed “Rubin,” will start mass manufacturing within the fourth quarter of 2025, with rack options following in early 2026.
The lineup’s inaugural chip, the R100, will advance to TSMC’s 3nm N3 node, proceed utilizing CoWoS-L packaging, incorporate a 4x reticle design, and have HBM4 reminiscence. The GR200 Grace CPU may also make the most of N3, transferring the whole system past Blackwell’s 5nm node.
