NVIDIA GeForce RTX 4080 SUPER 16GB Specifications for AI Enthusiasts
The NVIDIA GeForce RTX 4080 SUPER is a graphics card released in January 2024, featuring the Ada Lovelace architecture based on the fully enabled AD103 GPU with all 80 streaming multiprocessors active. It represents a mid-generation refresh of the RTX 4080, offering improved performance at a lower MSRP ($999 vs $1,199). With 10,240 CUDA cores, 320 4th-generation tensor cores, and 16GB of GDDR6X memory running at 23 Gbps, the RTX 4080 SUPER delivers 836 AI TOPS, making it excellent for both gaming and machine learning workloads. The card maxes out the AD103 silicon, similar to how the RTX 2080 Super maximized its predecessor's chip. It uses a PCI-Express 4.0 x16 host interface and features 736.6 GB/s memory bandwidth.
- GPU Architecture: ada
- Hardware-Accelerated GEMM Operations:FP16 FP32 BF16 FP8 INT8 INT4 TF32 FP64 INT1
- CUDA Compute Capability : 8.9
Specifications for NVIDIA GeForce RTX 4080 SUPER
| Raw Performance | |
|---|---|
| FP32 TFLOPs: 104.45 | |
| FP16 TFLOPs: 418.79 | |
| Tensor Core Count: 320 | |
| Memory Capacity (GB): 16 | |
| Memory Bandwidth (GB/s): 736.6 | |
| Int8 TOPs: 835.58 |
Real-time NVIDIA GeForce RTX 4080 SUPER GPU Prices
We're tracking 1 of the NVIDIA GeForce RTX 4080 SUPER GPUs currently available for sale. The lowest price is $1,900
Buy NowCompare Price/Performance to other GPUs
We track real-time prices of other GPUs too so that you can compare the price/performance of the NVIDIA GeForce RTX 4080 SUPER GPU to other GPUs.
Compare GPU Price/PerformanceReferences
- https://images.nvidia.com/aem-dam/Solutions/geforce/ada/nvidia-ada-gpu-architecture.pdf
- https://images.nvidia.com/aem-dam/Solutions/Data-Center/l4/nvidia-ada-gpu-architecture-whitepaper-v2.1.pdf
- https://www.nvidia.com/en-us/geforce/graphics-cards/40-series/rtx-4080-family/
- https://www.techpowerup.com/review/nvidia-geforce-rtx-4080-super-founders-edition/
- https://www.bestgpusforai.com/gpu-comparison/5090-vs-4080-super