The NVIDIA GeForce RTX 4080 is here, and we have a full review of the Founders Edition today to look at gaming in 4K and even 1440p, with a lot of comparisons. We will look at Ray Tracing performance, DLSS performance, test at 4K as well as 1440p, and even see how performance improves from the GeForce RTX 3080 directly to the new GeForce RTX 4080. We will also compare it against the RTX 3090 Ti, RTX 3090, RTX 3080 Ti, Radeon RX 6900 XT, and even Radeon RX 6800 XT.
Continuing the new GeForce RTX 40 series, the new GeForce RTX 4080 is one step down from the recently released GeForce RTX 4090 on October 11th, 2022. The GeForce RTX 4080 (formally called GeForce RTX 4080 16GB) has an MSRP of $1,199. Though the “16GB” naming scheme has been dropped from the Founders Edition, you will still see some partner boards using that designation in their product naming. The GeForce RTX 4080 has 16GB of GDDR6X on board, it’s just that technically you can drop the 16GB from the name and you will be correct in its naming, either way, will work, and you may see it marketed both ways. The Founders Edition, however, is just called GeForce RTX 4080.
The GeForce RTX 4080 is based on NVIDIA’s new Ada Lovelace architecture, built on a custom NVIDIA TSMC 4N process and based on the AD103 GPU. There are many new innovations in Ada Lovelace GPUs, which include improved Ray Tracing, improved Tensor Cores, Shader Execution Reordering, Displaced Micro-Meshes, Opacity Micro-Masks, FP8 Inferencing, improved Optical Flow Accelerator and DLSS 3 with Frame Generation. This adds onto additional features such as NVIDIA Reflex, NVIDIA RTX Remix, NVIDIA Broadcast, NVIDIA Studio, and NVIDIA Omniverse. For a more complete description of these new features and architecture, check out our GeForce RTX 4090 Review.
|GeForce RTX 4090
|GeForce RTX 4080
|TSMC 4N NVIDIA
|TSMC 4N NVIDIA
|L2 Cache Size
|128 (3rd Gen)
|76 (3nd Gen)
|512 (4th Gen)
|304 (4rd Gen)
The RTX 4080 graphics card is positioned as an ultra-performance enthusiast gamer and creator GPU. It uses 4th Generation Tensor Cores and 3rd Generation RT Cores. It has dual AVI Encoders. The 9,728 CUDA Cores provide 49 Shader-TFLOPS, the Tensor Cores offer 780 Tensor-TFLOPS and RT Cores are capable of 113 RT-TFLOPS. NVIDIA claims the RTX 4080 is twice as fast as the GeForce RTX 3080 Ti while using nearly 10% less power. In terms of power, NVIDIA stresses that different workloads naturally pull different Wattages of power as the demand dictates. In video playback and average gaming, the GeForce RTX 4080 should pull less power than the GeForce RTX 3090 and RTX 3090 Ti, including idle Wattage, with an overall lower 320W TGP.
NVIDIA GeForce RTX 4080 Founders Edition
The GeForce RTX 4080 Founders Edition uses a new design (while looking the same as the RTX 3090) that is tailored to increase airflow and make the heatsink more effective. The fans have grown slightly, but use fluid dynamic bearings and counter-rotating fans to result in cooler and quieter operation. The distance between the heatsink fins is slightly different. The GeForce RTX 4080 FE can achieve 15% more airflow than the RTX 3090 at the same acoustic level. The GeForce RTX 4080 FE measures 304mm in length, 137mm in width, and 61mm in height, 3-slot card. It exactly matches the GeForce RTX 4090 FE in dimensions.
The GeForce RTX 4080 requires a 750W minimum power supply. The RTX 4080 has two power compatibility options, it can accept 3x PCIe 8-pin cables from the power supply to the included RTX 4080 power connector adapter or 1x 450W 16-pin PCIe Gen 5 power cable from the power supply (12VHPWR).
The GeForce RTX 4080 supports 2x HDMI 2.1 and 3x DisplayPort 1.4a. It can run 4K at 240Hz or 8K at 60Hz with DSC. For the Founders Edition, the 3x 8-pin adapter to 16-pin connector is included in the box.