Wednesday, May 17th 2023
NVIDIA GeForce RTX 4060 Ti Shows Up in Geekbench Database
NVIDIA GeForce RTX 4060 Ti has been spotted in the Geekbench database, confirming previously rumored specifications. This also means that NVIDIA and its AIC board partners have already sent out sample to the reviewers which is how it probably ended up tested in Geekbench.
The information from the Geekbench results show 34 Multiprocessor Count, confirming 4352 CUDA cores, as well as 8 GB of VRAM clocked at 18 Gbps. The maximum boost is at 2.54 GHz but this would depend on the actual SKU, so it is possible we could see higher and lower boost clocks. The tested graphics card scores 146170 points in CUDA Geekbench 5 test, placing it just above the RTX 3060 Ti, and compared to some of the latest entries it should be at least around 9 percent faster. As rumored earlier, the NVIDIA GeForce RTX 4060 Ti 8 GB should launch on May 24th.
Sources:
Benchleaks at Twitter, Geekbench, via Videocardz
The information from the Geekbench results show 34 Multiprocessor Count, confirming 4352 CUDA cores, as well as 8 GB of VRAM clocked at 18 Gbps. The maximum boost is at 2.54 GHz but this would depend on the actual SKU, so it is possible we could see higher and lower boost clocks. The tested graphics card scores 146170 points in CUDA Geekbench 5 test, placing it just above the RTX 3060 Ti, and compared to some of the latest entries it should be at least around 9 percent faster. As rumored earlier, the NVIDIA GeForce RTX 4060 Ti 8 GB should launch on May 24th.
34 Comments on NVIDIA GeForce RTX 4060 Ti Shows Up in Geekbench Database
Harder and harder to get excited about GPU releases these days.
I'm hoping the RX 7600 will be priced well. The market needs a healthy, ~$250 graphics card, and AMD can deliver here.
I do wonder how did their fans get so utterly rabid sometimes, and I am guilty of poking and prodding the red bear more than just a few times (I can't help myself, AMD fans get genuinely angry when you criticize their products), but I guess if you look at the past (Intel playing dirty, Nvidia's unfriendly behavior, etc.) it becomes apparent as to why some people heavily favor team red with ideological fervor.
AMD was the only one to release budget GPUs last generation which were being sold at performance segment prices, Nvidia just ignored everything below the 3060, and eventually released a very late 3050 that made - and still makes no sense at the prices asked built out of harvested 3060's that didn't make the cut.
That would leave Intel free reign to capture the market both AMD and NVIDIA abandoned, the former x10 entry-level/passive discrete cards. With the GT 710 going EOL and receiving no further driver updates, there are no currently supported products at that level, except for the elusive and practically cancelled GT 1010 which never made to market. But that segment also is the one that won't have access to features like Resizable BAR and would genuinely care about stability, so they can't pitch the A310 there.
in the US going from 4080 to 4090 is like what 500-600 dollars... the price difference might not seem that big
but look at a country like new zealand an asus strix 4080 is $2899 NZD and a strix 4090 is $4599 NZD .. its $1700 dollars difference
but anything from 4070ti and below, the performance difference is not that big but the price between each of them is far and wide ..
i think nvidia has messed up the 40series pricing
There are still 100+ 3060Ti cards at my Micro Center and the lowest priced one (not counting one marked as "open box" and priced around $380) is $409.99.
Oughta relabel this as a 4050Ti ;)
*older MMOs that I've been playing for years
Inferring he is a Nvidia fanboy just because he speaks about AMD, is itself a statement of true fanboyism
NVOFA Application Note - NVIDIA Docs
And Covid pricing gave everyone the excuse to cram 4-5 years worth of price inflation into the space of 12 months. It's never going back down, and will only continue to rise until there's some kind of catastrophic real-world political event (unlikely) or AMD gets its ass in gear (only moderately likely). Until then, we get to enjoy Nvidia mislabeling each successive generation with model numbers (and prices) one performance level too high, increasing more with each generation.