The GeForce RTX 4070 was an obvious no-show during Nvidia’s GPU announcement yesterday. However, the company is planning to release one – along with the lower-end RTX 4000 models – in the near future once it starts ramping up production.
“We don’t have everything ready to publish at once,” Nvidia CEO Jensen Huang said in a Q&A with reporters on Wednesday. “What we have ready are the 4090 and the 4080. But over time, we will be bringing other products at the lower ends of the stack to market.”
The statement also notes that RTX 4000 GPUs will eventually reach more consumer-friendly price points. Currently, the most affordable product in the series is the 12GB GeForce RTX 4080 card, which arrives in November with a starting price of $899.
The other two products, the 16GB RTX 4080 and RTX 4090, start at $1,199 and $1,599 respectively, putting them out of reach for consumers hoping for a mid-range PC graphics card.
Jensen said the reason why Nvidia is ignoring the mid- and low-end market right now is “simple” and “not very complex.” “We usually start at the top level because that’s where enthusiasts want to update first. And what we’ve found is 4080, 4090 is a good place to start. And as quickly as we can, we’ll move down the stack,” he said.
However, Nvidia made an interesting decision to sell two completely different RTX 4080 models, even though they share the same name. That’s because the 12GB model not only has less video memory, but only 7680 CUDA cores. Meanwhile, the 16GB model has a significantly higher core count than CUDA at 9728. Both models also use different GPU chips, powered by the company’s Ada Lovelace architecture.
As a result, some critics(Opens in a new window) He claims that the 12GB RTX 4080 is actually a convincing 4070 model, but with a $400 price increase over the RTX 3070, which was originally launched for two years starting at $499.
However, Nvidia sees things differently. In a separate Q&A with reporters, company executives said the RTX 4080 12GB is a “high-performance GPU” that can 3 times outperform the old RTX 3080 12GB.
Recommended by our editors
“We really think it’s worthy of an 80’s product. That’s the real reason it’s called that way,” says one executive. In other words, Nvidia is keeping the RTX 4070 for a low-power GPU.
Nvidia is also facing an oversupply situation with the older RTX 3000 series. Demand for the GPU has fallen to the point that retailers are slashing prices to help sell existing inventory. So it’s likely that Nvidia will wait for current supplies to be evacuated before releasing the RTX 4070 and other lower-end models. Otherwise, any remaining stock of the RTX 3000 cards may fail to budge.
The Nvidia CEO added: “I hope by the Q4 timeframe, sometime in Q4, the (sales) channel will normalize, and set the stage for a great launch for Ada.”
Get our best stories!
sign for What’s new now To deliver our most important news to your inbox every morning.