NVIDIA GeForce RTX 4080 SUPER
An Ada Lovelace graphics card with 10,240 CUDA cores, 16 GB of GDDR6X on a 256-bit bus, DLSS 3.5 with Frame Generation, dual NVENC encoders and a 320 W board power.

Full Specification Sheet
| Architecture | NVIDIA Ada Lovelace |
|---|---|
| CUDA Cores | 10,240 |
| Boost / Base Clock | 2.55 GHz / 2.29 GHz |
| Memory | 16 GB GDDR6X, 256-bit |
| Tensor Cores | 4th generation, 836 AI TOPS |
| RT Cores | 3rd generation, 121 RT TFLOPS |
| Shader Throughput | 52 TFLOPS |
| Interface | PCI Express Gen 4 |
| Total Graphics Power | 320 W |
| Required System Power | 750 W |
| Power Connector | 3x PCIe 8-pin (adapter in box) or 1x 450 W or greater PCIe Gen 5 cable |
| Display Outputs | HDMI 2.1a, 3x DisplayPort 1.4a; up to 4 displays |
| Founders Edition Size | 304 mm long, 137 mm wide, 3-slot |
The NVIDIA GeForce RTX 4080 SUPER is a high-end graphics card from the GeForce RTX 40 series, built on the Ada Lovelace architecture. NVIDIA presents it together with the original GeForce RTX 4080 as a family powered by the ultra-efficient Ada Lovelace architecture and 16 GB of fast G6X memory, and its own headline for the family is SUPER Fast. SUPER Powered. The SUPER model has more CUDA cores, slightly higher clocks and more throughput than the RTX 4080 it complements, while keeping the same memory size and the same 320 W board power. This page collects the specification NVIDIA publishes for the Founders Edition and reference design, explains what the numbers mean and marks clearly which statements are NVIDIA's own. The page gives no price for the SUPER model, and we make no benchmark claims.
Cores and clocks
The card has 10,240 CUDA cores, compared with 9,728 on the RTX 4080. NVIDIA lists a base clock of 2.29 GHz and a boost clock of 2.55 GHz, against 2.21 GHz and 2.51 GHz for the RTX 4080. The listed peak throughput is 52 TFLOPS for the shader cores, 121 TFLOPS for the third-generation RT cores and 836 AI TOPS for the fourth-generation Tensor cores, against 49, 113 and 780 for the RTX 4080. These are theoretical peak rates and not a prediction of frame rates. The gap between the two models is therefore a modest step in core count and throughput rather than a different class of card. NVIDIA's marketing for the architecture makes three headline claims: new streaming multiprocessors with up to twice the performance and power efficiency, fourth-generation Tensor cores with up to four times the performance using DLSS 3 versus brute-force rendering, and third-generation RT cores with up to twice the ray tracing performance. Those are the manufacturer's comparative claims against the previous generation.
Memory
The memory configuration is 16 GB of GDDR6X on a 256-bit interface. Sixteen gigabytes is a comfortable capacity for current games at high resolutions and for many creative applications, and the 256-bit width is wider than on the mid-range cards of the same generation. Our guide to 8 GB versus 24 GB of video memory explains when capacity limits performance and when it does not. The page does not publish a memory bandwidth figure, so we do not quote one.
DLSS 3.5, ray tracing and Reflex
The card supports NVIDIA DLSS 3.5, which the specification table lists as Super Resolution, DLAA, Ray Reconstruction and Frame Generation. NVIDIA explains that DLSS 3 uses the fourth-generation Tensor cores and the Optical Flow Accelerator to create additional frames with AI and improve image quality. The card also supports NVIDIA Reflex, a low-latency platform that the manufacturer says is built to optimise and measure system latency, and ray tracing through the third-generation RT cores. NVIDIA's performance charts for the family compare the RTX 4080 SUPER with the RTX 3080 Ti and the RTX 2080 SUPER at 3840 by 2160 in demanding ray-traced titles with DLSS and Frame Generation enabled; they are marketing comparisons that depend on those settings, and we do not reproduce their numbers.
Display and video capabilities
Display outputs are one HDMI 2.1a and three DisplayPort 1.4a connectors. The maximum display resolution is listed as 4K at 240 Hz or 8K at 60 Hz with Display Stream Compression and HDR, and NVIDIA notes that with dual DisplayPort 1.4a and DSC, 8K HDR at 120 Hz is possible. Up to four independent displays are supported, at 4K and 120 Hz using DisplayPort or HDMI, or two displays at 4K and 240 Hz or 8K and 60 Hz with DSC. HDCP 2.3 is supported. For video work, the card has two eighth-generation NVIDIA encoders (NVENC) and a fifth-generation decoder, with AV1 encode and decode. NVIDIA presents AV1 encoding as more efficient than H.264 for streaming at higher resolutions, and the extra encoder is relevant to creators who record or stream at high quality. The NVIDIA Broadcast app, RTX Video Super Resolution, NVIDIA Studio drivers and the Omniverse platform are listed among the supported features.
Power requirements
Total graphics power is 320 W for both the SUPER and the original model, and NVIDIA lists a required system power of 750 W, based on a PC configured with a Ryzen 9 5900X processor, adding that requirements can differ with the system configuration. The power connection is either three PCIe 8-pin cables from the power supply to the included adapter, or a single PCIe Gen 5 cable rated at 450 W or more. That connector arrangement matters for the build: read our explanation of the 12VHPWR power connector before you plug in, and our guide to daisy-chained GPU power cables and adapters for the safe way to connect multiple 8-pin cables. The maximum GPU temperature is listed as 90 degrees Celsius. NVIDIA also publishes idle power of 15 W, video playback power of 22 W and average gaming power of 246 W for the SUPER, against 13 W, 21 W and 251 W for the original, measured across 22 games at 4K, 1440p and 1080p on the Founders Edition or reference design.
Size and compatibility
The Founders Edition is 304 mm long, 137 mm wide and takes up three slots, so it needs a case with enough length and clearance and a motherboard layout that leaves room for the thickness of the cooler. Partner cards vary in size, so check each one. The card uses a PCI Express Gen 4 interface, and NVIDIA lists Resizable BAR support, G-SYNC, NVIDIA App or GeForce Experience, ShadowPlay, DirectX 12 Ultimate, Vulkan and OpenGL 4.6. Multi-GPU NVLink is not supported. The card is marked as VR ready.
Founders Edition versus partner cards
NVIDIA states that the figures represent the Founders Edition or reference design and that clock specifications apply while gaming with medium to full GPU utilisation. Specifications may vary by add-in-card manufacturer, whose own websites hold the shipping specifications for each model. A partner card can therefore have a different factory boost clock, cooler, length and connector arrangement, so always compare the partner's own sheet for the exact product you plan to buy.
Where it fits
The GeForce RTX 4080 SUPER is aimed at high-resolution gaming with ray tracing and at creative workloads, one step below the flagship. Within this site, the natural comparisons are the RTX 4080 SUPER versus RTX 4090 comparison for the tier above, and the AMD Radeon RX 7900 XTX as a competing high-end card. You can browse all cards in the graphics card category. This page states no price, so check current price and availability with a retailer. None of the statements above is a test result; all values are NVIDIA's published specifications.
Product image: NVIDIA product image.


