

GeForce RTX 4080 Super wins 14 of 31 benchmarks, averaging -1.3% faster.
Both cards' numbers are anchored estimates calibrated against our measured cards, pending first-party measurement. Treat small gaps as ties.
The gap is widest in Z-Image Turbo, where NVIDIA GeForce RTX 4080 leads by 33% (3.07 vs 2.3 images/min); the closest fight is PixArt-Sigma XL (0% apart).
| Benchmark | NVIDIA GeForce RTX 4080 | GeForce RTX 4080 Super | Difference |
|---|---|---|---|
| MiniCPM5 2B tok/s | 312.75 | 311.94 | 0% |
| LFM2.5 2.6B tok/s | 307.16 | 308.63 | -0% |
| Granite 4.1 3B tok/s | 226.16 | 227.06 | -0% |
| Nemotron 3 Nano 4B tok/s | 198 | 200.69 | -1% |
| Qwen3 4B tok/s | 201.76 | 197.53 | +2% |
| DeepSeek Coder 7B Instruct v1.5 tok/s | 143.42 | 146.98 | -2% |
| Llama 3 8B tok/s | 127.3 | 130.53 | -2% |
| Llama 3.1 8B tok/s | 127.09 | 126.29 | +1% |
| Qwen3 8B tok/s | 123.68 | 126.39 | -2% |
| Nemotron Nano 9B v2 tok/s | 91.27 | 93.43 | -2% |
| Ornith 1.5 9B tok/s | 109.71 | 111.6 | -2% |
| Gemma 4 12B tok/s | 78.94 | 80.57 | -2% |
| Qwen2.5-Coder 14B tok/s | 69.93 | 70.55 | -1% |
| Qwen3 14B tok/s | 70.88 | 72.96 | -3% |
| Gemma 4 26B A4B tok/s | 0 | 0 | n/a |
| Qwen3 30B A3B tok/s | 0 | 0 | n/a |
| Gemma 4 31B tok/s | 0 | 0 | n/a |
| Qwen3 32B tok/s | 0 | 0 | n/a |
| Llama 3.3 70B tok/s | 0 | 0 | n/a |
| Stable Diffusion 1.5 images/min | 51.23 | 51.96 | -1% |
| SDXL Turbo images/min | 484.82 | 410.08 | +18% |
| Z-Image Turbo images/min | 3.07 | 2.3 | +33% |
| Sana 1.6B images/min | 27.92 | 26.98 | +3% |
| Stable Diffusion XL images/min | 10.16 | 11.54 | -12% |
| Playground v2.5 images/min | 6.33 | 6.74 | -6% |
| PixArt-Sigma XL images/min | 14.6 | 14.59 | 0% |
| FLUX.1 Kontext dev images/min | 0 | 0 | n/a |
| FLUX.1 dev images/min | 0 | 0 | n/a |
| Qwen-Image-Edit images/min | 0 | 0 | n/a |
| LTX-Video (distilled) frames/s | 3.705 | 2.853 | +30% |
| Wan 2.2 5B (720p) frames/s | 0 | 0 | n/a |
How long each card takes to finish a complete pipeline, not just one model. NVIDIA GeForce RTX 4080 is faster on 0 of 1; GeForce RTX 4080 Super on 1.
| Workflow | NVIDIA GeForce RTX 4080 | GeForce RTX 4080 Super | Difference | Cost per run |
|---|---|---|---|---|
| Full codebase review | 14.3 min | 14.2 min | GeForce RTX 4080 Super 1.01x faster | $0.054 vs $0.052 |
Renting by the hour, GeForce RTX 4080 Super finishes 1 of 1 cheaper. The quicker card is not automatically the cheaper way to get the work done.
| Card | Per hour |
|---|---|
| NVIDIA GeForce RTX 4080 | $0.228 |
| GeForce RTX 4080 Super | $0.222 |
GeForce RTX 4080 Super is 1.03x cheaper per hour. Cheapest on-demand rate we see across RunPod and Vast.
| NVIDIA GeForce RTX 4080 | GeForce RTX 4080 Super | |
|---|---|---|
| VRAM | 16GB | 16GB |
| Transistors | 45,900M | 45,900M |
| Die size | 378.6 mm² | 378.6 mm² |
| Process node | 4 nm | 4 nm |
| Transistor density | 121.2 M/mm² | 121.2 M/mm² |
| Architecture | Ada Lovelace (AD103) | Ada Lovelace |
| Memory bandwidth | 716.8 GB/s | 736 GB/s |
| Boost clock | 2,505 MHz | 2,505 MHz |
| TDP | 320 W | 320 W |
| Launch MSRP | $1,199 | $999 |
| Release | 2022-11-16 | 2024-01-31 |
NVIDIA GeForce RTX 4080 full review · GeForce RTX 4080 Super full review · All AI & Machine Learning rankings