In case you missed it, NVIDIA "unlaunched" the GeForce RTX 4080 12 GB; and so the RTX 4080 16 GB is now called just "RTX 4080." Here are some of the first pictures of a custom-design RTX 4080, the GIGABYTE Eagle OC. The company's new value-ended factory-overclocked graphics card brand sheds much of the unnecessary design bulk of the RTX 30-series Eagle; and sticks with a functional, minimalist design. The card features a 4-slot cooling solution, with an enormous plastic cooler shrooud holding a trio of what look like 100 mm fans. ventilating a dual aluminium fin-stack heatsink. Display outputs include a trio of DisplayPort 1.4a, and an HDMI 2.0b. The card draws power from a single 16-pin 12VHPWR connector, and is possibly the first confirmation that NVIDIA is extending the new power connector down its product stack. The RTX 4080 has a typical board power of 320 W (at reference speeds).

Based on the 4 nm AD103 silicon, the RTX 4080 is endowed with 9,728 CUDA cores, 76 RT cores, 304 Tensor cores, 304 TMUs, and 112 ROPs. The card's 16 GB of GDDR6X memory runs across a 256-bit wide memory interface, which at its memory frequency of 23 Gbps, churns out 736 GB/s of memory bandwidth. GIGABYTE is designing the Eagle brand-extension to compete with the likes of the ASUS TUF Gaming, and MSI Ventus X. NVIDIA is launching the RTX 4080 on November 16.

Here's our first look at the "AD103" and "AD104" chips powering the GeForce RTX 4080 16 GB and RTX 4080 12 GB, respectively, thanks to Ryan Smith from Anandtech. These are the second- and third-largest implementations of the GeForce "Ada" graphics architecture, with the "AD102" powering the RTX 4090 being the largest. Both chips are built on the same TSMC 4N (4 nm EUV) silicon fabrication process as the AD102, but are significantly distant from it in specifications. For example, the AD102 has a staggering 80 percent more number-crunching machinery than the AD103, and a 50 percent wider memory interface. The sheer numbers at play here, enable NVIDIA to carve out dozens of SKUs based on the three chips alone, before we're shown the mid-range "AD106" in the future.

The AD103 die measures 378.6 mm², significantly smaller than the 608 mm² of the AD102, and it reflects in a much lower transistor count of 45.9 billion. The chip physically features 80 streaming multiprocessors (SM), which work out to 10,240 CUDA cores, 320 Tensor cores, 80 RT cores, and 320 TMUs. The chip is endowed with a healthy ROP count of 112, and has a 256-bit wide GDDR6X memory interface. The AD104 is smaller still, with a die-size of 294.5 mm², a transistor count of 35.8 billion, 60 SM, 7,680 CUDA cores, 240 Tensor cores, 60 RT cores, 240 TMUs, and 80 ROPs. Ryan Smith says that the RTX 4080 12 GB maxes out the AD104, which means its memory interface is physically just 192-bit wide.