Nvidia Rumored to Unveil Three GeForce RTX 4060-Series Cards in May, Up to 16GB
But only one will be available this month.
Nvidia is rumored to announce three GeForce RTX 4060-series graphics cards this month, but only one of them is said to be available in May, whereas others will purportedly hit the market in July, according to renowned hardware leaker @MegaSizeGPU, who has been accurate in the past when it comes to Nvidia's launch plans. The leader says that Nvidia’s GeForce RTX 4060 lineup will include graphics cards with 8GB and 16GB of memory.
Later this month, Nvidia is rumored to introduce three Ada Lovelace-based GeForce RTX 4060-series graphics cards aimed at the mainstream and performance-mainstream market segments. The lineup will purportedly include the GeForce RTX 4060 Ti with 8GB of GDDR6 SGRAM, the GeForce RTX 4060 Ti with 16GB of memory, and the GeForce RTX 4060 with 8GB of GDDR6 memory. However, only the GeForce RTX 4060 Ti 8GB is expected to hit the market this month. According to the leaker, the more expensive and cheaper models will be available only in July.
Row 0 - Cell 0 | GPU | FP32 CUDA Cores | Memory Configuration | TBP | MSRP |
GeForce RTX 4090 Ti | AD102 | 18176 (?) | 24GB 384-bit 24 GT/s GDDR6X (?) | 600W (?) | ? |
GeForce RTX 4090 | AD102 | 16384 | 24GB 384-bit 21 GT/s GDDR6X | 450W | $1,599 |
GeForce RTX 4080 | AD103 | 9728 | 16GB 256-bit 22.4 GT/s GDDR6X | 320W | $1,199 |
GeForce RTX 4070 Ti | AD104 | 7680 | 12GB 192-bit 21 GT/s GDDR6X | 285W | $799 |
GeForce RTX 4070 | AD104 | 5888 | 12GB 192-bit 21 GT/s GDDR6X | 200W | $599 |
GeForce RTX 4060 Ti* | AD106 | 4352 (?) | 8GB or 16GB 128-bit 18 GT/s GDDR6 (?) | 160W (?) | sub-$500 |
GeForce RTX 4060* | AD106 | 3072 (?) | 8GB 128-bit GDDR6 | ? | sub-$400 (?) |
*Rumored specs, not confirmed by Nvidia
At this point, it is unclear whether Nvidia's GeForce RTX 4060 Ti 8GB and 16GB will rely on the AD104 graphics processor in the same configuration with 4352 CUDA cores, but this is certainly a likely scenario. Based on previous leaks, Nvidia wants its RTX 4060 Ti to consume no more than 160W, which will enable GPU makers to build compact yet rather powerful performance-mainstream boards and therefore address both standard and compact desktops.
As for the vanilla GeForce RTX 4060, it will feature AD106 with 3072 CUDA cores and will therefore consume even less power, so expect low-profile and perhaps even single-slot graphics cards based on this GPU.
As of now, it does not look like Nvidia has a firm launch date for its new products. The green company might formally introduce its GeForce RTX 4060 family later this month, and perhaps it will use the company's chief executive Jensen Huang's keynote at Computex 2023 trade show on May 29 to do so. Yet, in this case it means that the GeForce RTX 4060 Ti 8GB will be on sale for just a couple of days this month.
Anyhow, since the information comes from an unofficial (yet credible) source, take it with a grain of salt since even if it represents current plans, intentions tend to change.
Stay On the Cutting Edge: Get the Tom's Hardware Newsletter
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Anton Shilov is a contributing writer at Tom’s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends.
-
At this point, it is unclear whether Nvidia's GeForce RTX 4060 Ti 8GB and 16GB will rely on the AD104 graphics processor in the same configuration with 4352 CUDA cores, but this is certainly a likely scenario.
The RTX 4060 Ti will utilize the AD106-350-A1 GPU core, and not 104, which is slightly a cut-down version of the full AD106 graphics chip. This should give the card 34 SMs or 4352 CUDA cores, 16/8 GB GDDR6 memory running at 18 Gbps across a 128-bit bus interface, and 288 GB/s of bandwidth.
There's also 32 MB of L2 cache. According to previous leaks, the 16 GB variant utilizes the PG190 SKU 363 PCB, while the 8 GB variant utilizes the PG190 SKU 361 PCB.
I think the 190 PCB might be used for the Founder's Edition model, and reference AIB cards should sport the PG173 board instead.
As for the vanilla GeForce RTX 4060, it will feature AD106 with 3072 CUDA cores and will therefore consume even less power, so expect low-profile and perhaps even single-slot graphics cards based on this GPU.
No, the RTX 4060 will actually sport the AD107-400-A1 GPU, the fully enabled AD107 die (PG173 SKU 371 PCB design). The current GeForce RTX 4060 Laptop GPU also comes in the same config.
So based on this, the card should get 3072 CUDA cores and 8 GB of GDDR6 memory running at 18 Gbps memory speeds across a 128-bit bus interface, within a 110W - 115W reference TDP. And obviously, it will also sport 24 MB of cache (L2). -
-Fran- If they do release a 16GB variant of any of the 4060's, then I'll give a nod to Jensen, for sure.Reply
Not because this tier needs the 16GB badly, but this tier is definitely a great trade off for budget enthusiasts to get into AI and other non-gamer stuffs, including video editing and such. It does look kind of dumb on paper, but it is something I'd celebrate more than mock at this point.
Regards. -
Order 66 If Nvidia could find the mercy to launch the 4060 ti 16GB at $429 and the 8GB model at $399 and the 4060 at $349 that would be great bang for the buck, especially considering how this generation has gone so far for Nvidia.Reply -
DookieDraws All I would like to know is; when are the 4070 and 4070 Tis coming with 16GB? Will this be the 4070 Super, and the 4070 Ti Super Duper variants? Come on, Mr. Leather Jacket! You have enough jackets for now. Stop this nonsense and give the people what they want.Reply -
atomicWAR I am happy to see a 16GB option but not exactly surprised as ther 60(Ti) class cards typically has two different memory skus. Unfortunately for now it seems 16GB is limited to the Ti model. I would really like to see a base RTX 4060 16GB as well as a RTX 4070 (Ti)/4080 with more ram as well. I prefer a memory bus that isn't hobbled in the case of the 70/80 class but depending on their performance when using greater than 12/16GB respectively, I might be convinced. I still have one more PC to build this year after I finish my wifes which is on hold until the Ryzen X3D gets squared away without a bug riddled firmware like currently. Point being I would love to see a higher capacity 70 (Ti) class option for my nephew's build.Reply -
atomicWAR
Unfortunately without hobbling the memory bus its not possible at this time using the AD104 die unless they use different silicon. But they could use cut down AD103 die (ie 4080) to pull it off though I find that unlikely for a base RTX 4070 due to costs...but the 4070Ti, that I could see.DookieDraws said:All I would like to know is; when are the 4070 and 4070 Tis coming with 16GB? Will this be the 4070 Super, and the 4070 Ti Super Duper variants? Come on, Mr. Leather Jacket! You have enough jackets for now. Stop this nonsense and give the people what they want. -
hannibal How they could do 16Gb with 128bit memory bus?Reply
There are not even 3Gb memory chips, not to talk about 4Gb memory chips. Without those 16gb is just impossible, unles they have very complex memory handling system that divides normal 32 but bus to two... Sound really slow, if that would be true.
So I don´t believe this rumor! Too much that does not make sense... We know that 3gb memory chips are supposed to be in development so 12Gb would be possible sometimes in the future. Is there 4gb chips even in preproduction? Most likely in development though... but that can mean anything to one year to couple of years to come to the market. -
peterf28 I am not even interested in the RTX 4000 series anymore, I am sicken with what NVIDIA is pulling off. I just don't want to read about this crap anymore. Ignoring 4000 series from now on totally, not even reading articles.Reply