According to a tweet by resident GPU leaker, Kopite7kimi, the GeForce RTX 4060 (AD106) reportedly delivers a TimeSpy Extreme score of 7,000 points. If accurate, it would put the GeForce RTX 4060’s performance in between the RTX 3060 Ti and RTX 3070. Also, Kopite7kimi noted that Nvidia’s AD106 and the more budget-friendly AD107 die would only have eight PCIe lanes at their disposal instead of 16.
It is the first time we’ve gotten a TimeSpy Extreme performance figure from the hardware leaker regarding Nvidia’s RTX 40-series (Ada Lovelace) GPUs. AD106 will potentially power the next-generation RTX 4060 and possibly the RTX 4050 Ti (if Nvidia makes one this time).
Kopite7kimi stated that the new score is not very strong, but we would beg to differ. For reference, the current RTX 3060 has an average TimeSpy Extreme graphics score of around 4,500 points to 4,800 points. So if Kopite7kimi’s data is accurate and the RTX 4060 AD106 GPU has a TimeSpy Extreme score of approximately 7,000, the RTX 4060 is effectively 50% faster than the RTX 3060.
It would put the AD106 die, or rather RTX 4060, at performance parity with cards like the RTX 3060 Ti and RTX 3070, which isn’t the wrong place to be. According to TimeSpy Extreme alone, the RTX 4060 appears to be a good upgrade over the RTX 3060. But that is the problem; we only have the alleged TimeSpy Extreme scores on a GPU that isn’t yet out. So as always, take this data with a grain of salt. However, we will say that the RTX 4060’s estimated performance looks very accurate if history repeats itself.
When the RTX 3060 was released, its performance generally outperformed the RTX 2060 Super and RTX 2070 by a few percentage points. The RTX 4060 would be doing the same thing here, being substantially quicker than the RTX 3060, but performing similarly to the RTX 3060 Ti and RTX 3070.
PCIe Lane Limitations
Arguably the most exciting part about the Tweet is the claims of the AD106 and AD107 getting nerfed to eight PCIe lanes instead of the traditional 16. AMD does the same thing with its entry-level Radeon RX 5000 and mid-range RX 6000 series product stack. It would seem that Nvidia will follow suit with the GeForce RTX 40-series.
Assuming Nvidia decides to use PCIe 4.0 instead of PCIe 5.0, we don't believe it will be a problem on modern platforms. For example, for an RTX 4050 and RTX 4060, a PCIe 4.0 x8 configuration should be adequate and provide enough bandwidth for PCIe heavy applications. After all, PCIe 4.0 x8 features the same bandwidth as PCIe 3.0 x16, and the RTX 2080 Ti - the last GPU to run PCIe 3.0, ran just fine with a PCIe 3.0 x16 interface.
The only potential issue with PCIe 4.0 x8 is that older systems are limited to PCIe 3.0 speeds. It, in turn, will force PCIe 4.0 x8 GPUs to alternate to PCIe 3.0 x8, which is much slower than PCIe 3.0 x16 and PCIe 4.0 x8. As a result, we could see FPS reductions due to the PCIe bottleneck, but we can't be sure until we get our hands on Nvidia's RTX 4050 and RTX 4060.
Wouldn't affect me, since I'm using an Zen2 X570 platform. But some of my friends are using Comet Lake or Coffee Lake, which are limited to PCIe 3.0. Coffee Lake may be getting old, but its i7 CPUs are still very relevant... but they may be a bit screwed if they planned on upgrading to a mainstream Ada Lovelace card. Or maybe not... Hopefully 8 lanes in a PCIe 3.0 slot won't have too much of a performance loss. Maybe it'll be fine. And maybe it won't even happen.
At least, a ~50% performance increase gen-over-gen for the card (purported equivalent segment SKU?) is quite impressive. I wonder how the power figures look.
so somehow between a 3060ti & a 3070 base is same thing as 3060 beating 2060 super & a 2070?
how does 3060 beating a 2070 become same as coming between a 3060ti and a 3070?
its not beating the 3070 like the it beat the 2070.
also fact Nvidia's pricing is seeming to be raised (as they plan for 30 and 40 series to coexist and prices...not a good sign) so the cost to performance is less than 30 series.
Well, not nice to people who has a little but older platform, but all in all. It makes more sense to buy used GPU with full 16 bit in anyway to those older machines! Cheaper, more speed than you can get from the new and no band wide problems.
They really try to cut cost by any means possible...
They'll keep selling 30xx GPUs when the new cards are out. This will give one good reason to buy the old cards.
Everybody only cares about PCIe x16 or x8, even x4 gets more love.
Nobody wants to implement x12, despite the fact that it's been part of the PCIe spec for lane configurations since day one.