As we march into the launch of NVIDIA's next-gen GeForce RTX 40 series "Ada Lovelace" GPUs, we're hearing more about the Ada launch lineup: GeForce RTX 4090, GeForce RTX 4080 16GB, and GeForce RTX 4080 12GB according to the latest leaks.
NVIDIA will be launching the GeForce RTX 4090 in all its next-gen GPU glory in October, but in November we'll be greeted by not one, but two new GeForce RTX 4080 graphics cards. The first is the higher-end GeForce RTX 4080 with 16GB of GDDR6X memory, clocked at a higher 23Gbps bandwidth for up to 768GB/sec of memory bandwidth.

The custom ASUS ROG Strix GeForce RTX 3080 OC Edition graphics card
Inside, the GeForce RTX 4080 16GB will use the new AD103-300 GPU with 9728 CUDA cores, with a GPU boost of up to 2505MHz (nearly the same as the RTX 4090, with a boost clock of up to 2520MHz). NVIDIA's new GeForce RTX 4080 has a default TGP of 340W, while it can be modified up to its maximum power limit of 516W. Remember, the 340W + 516W power numbers are for the RTX 4080 16GB graphics card model.
The second GeForce RTX 4080 graphics card will feature a cut-down AD104-400 GPU with 7680 CUDA cores, and would normally be what NVIDIA would call the GeForce RTX 4070 Ti or RTX 4070. Instead, NVIDIA has made a "last-minute name change" for this model says VideoCardz. Instead of the RTX 4070 Ti or RTX 4070, in its place, we have the RTX 4080 12GB.
RTX 4090, RTX 4080 16GB, RTX 4080 12GB TGP (default, maximum)
- RTX 4090 24GB (default 450W, up to 660W)
- RTX 4080 16GB (default 340W, up to 516W)
- RTX 4080 12GB (default 285W, up to 366W)
RTX 4090, RTX 4080 16GB, RTX 4080 12GB memory + bandwidth
- RTX 4090 24GB GDDR6X @ 21Gbps (up to 1008GB/sec memory bandwidth)
- RTX 4080 16GB GDDR6X @ 23Gbps (up to 736GB/sec memory bandwidth)
- RTX 4080 12GB GDDR6X @ 21Gbps (up to 504GB/sec memory bandwidth)
NVIDIA's second GeForce RTX 4080 will drop down from 16GB of GDDR6X memory to 12GB of GDDR6X memory, as well as down from 23Gbps bandwidth down to 21Gbps bandwidth. The power consumption on the RTX 4080 12GB is also much lower, with a default TGP of 285W and a maximum of 366W TGP.
That means the RTX 4080 16GB and RTX 4080 12GB have a rather significant difference in power numbers, with the RTX 4080 16GB's default TGP being 340W, it's 55W higher than the 285W from the RTX 4080 12GB. As for the maximum TGP, the RTX 4080 16GB has 516W which is a whopping 150W higher than the RTX 4080 12GB.

COLORFUL iGame GeForce RTX 3080 Vulcan OC
A couple of weeks ago we heard about the higher-end GeForce RTX 4080 with 16GB of GDDR6X memory featuring a higher-end 12-layer PCB, compared to the 10-layer PCB on the regular RTX 4080 12GB graphics card. For reference, the RTX 4090 has a 14-layer PCB according to the very latest leaks.
We should expect a hefty performance upgrade with the RTX 4080 16GB, which should kinda become the new GeForce RTX 3090 Ti competitor but in Ada Lovelace form... leaving the RTX 3090 Ti destroyer to the RTX 4090. Still, the RTX 4080 16GB is going to be a force to be reckoned with, especially in the beautiful NVIDIA GeForce RTX 4080 Founders Edition form and in custom AIB form where I'm sure we're going to see thermal systems ready for 516W+ and max power limits reached with joy.
- Read more: NVIDIA launch rumor: GeForce RTX 4090 first, RTX 4080 + RTX 4070 after
- Read more: NVIDIA GeForce RTX 4090 rumor: August launch, RTX 4080 in September
We initially heard about NVIDIA's new GeForce RTX 4080 and GeForce RTX 4070 launching in September, but those plans have changed in a few ways: first, there's no RTX 4070 launching now (RTX 4080 12GB is the "new" RTX 4070 or whatever x070-class release NVIDIA had planned) and they also missed their launch window, delayed into November.
The rumors in the links above are from all the way back in May.