GeForce GTX 1080 Ti vs NVIDIA GeForce RTX 2080 Ti Founders Edition, AI & Machine Learning Comparison
NVIDIA GeForce RTX 2080 Ti Founders Edition wins 3 of 16 benchmarks, averaging 111.1% faster.
Both cards' numbers are anchored estimates calibrated against our measured cards, pending first-party measurement. Treat small gaps as ties.
What the numbers say
The gap is widest in Stable Diffusion XL, where NVIDIA GeForce RTX 2080 Ti Founders Edition leads by 149% (1.68 vs 4.18 images/min); the closest fight is Qwen3-4B (90% apart); VRAM decides part of this one: GeForce GTX 1080 Ti runs 7 of our 12 AI workloads while the other card runs 3, models that don't fit score zero.
Benchmark results head-to-head
| Benchmark | GeForce GTX 1080 Ti | NVIDIA GeForce RTX 2080 Ti Founders Edition | Difference |
|---|---|---|---|
| Qwen3-4B tok/s | 78.25 | 148.46 | -47% |
| Llama-3.1-8B tok/s | 50.52 | 98.34 | -49% |
| Qwen2.5-Coder-14B tok/s | 27.36 | 0 | n/a |
| 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 XL images/min | 1.68 | 4.18 | -60% |
| PixArt-Sigma XL images/min | 0 | 0 | n/a |
| 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 |
| Z-Image Turbo images/min | 0 | 0 | n/a |
| LTX-Video (distilled) frames/s | 0 | 0 | n/a |
| Wan 2.2 5B (720p) frames/s | 0 | 0 | n/a |
Cost to rent
| Card | Per hour |
|---|---|
| GeForce GTX 1080 Ti | $0.065 |
| NVIDIA GeForce RTX 2080 Ti Founders Edition | $0.101 |
GeForce GTX 1080 Ti is 1.55x cheaper per hour. Cheapest on-demand rate we see across RunPod and Vast.
Specifications compared
| GeForce GTX 1080 Ti | NVIDIA GeForce RTX 2080 Ti Founders Edition | |
|---|---|---|
| VRAM | 11GB | 11GB |
| Transistors | 12,000M | 18,600M |
| Die size | 471 mm² | 754 mm² |
| Process node | 16 nm | 12 nm |
| Transistor density | 25.5 M/mm² | 24.7 M/mm² |
| Architecture | Pascal (GP102) | Turing (TU102) |
| Memory bandwidth | 484 GB/s | 616 GB/s |
| Boost clock | 1,582 MHz | 1,545 MHz |
| TDP | 250 W | 250 W |
| Launch MSRP | $699 | $1,199 |
| Release | 2017-03-10 | 2018-09-20 |
FAQ
- Which is better for ai & machine learning: GeForce GTX 1080 Ti or NVIDIA GeForce RTX 2080 Ti Founders Edition?
- NVIDIA GeForce RTX 2080 Ti Founders Edition performs better for ai & machine learning, winning 3 of 16 benchmarks in our suite with an average 111.1% advantage.
- What are the main hardware differences between GeForce GTX 1080 Ti and NVIDIA GeForce RTX 2080 Ti Founders Edition?
- GeForce GTX 1080 Ti has 11GB VRAM and a 250W TDP, while NVIDIA GeForce RTX 2080 Ti Founders Edition has 11GB VRAM and a 250W TDP.
- Does VRAM matter more than speed between GeForce GTX 1080 Ti and NVIDIA GeForce RTX 2080 Ti Founders Edition?
- For AI, yes, GeForce GTX 1080 Ti fits 1 more of our 12 workloads than NVIDIA GeForce RTX 2080 Ti Founders Edition. A model that exceeds VRAM doesn't run slower, it doesn't run at all, so the card that fits the model wins that workload outright.
- Where is the biggest performance difference between GeForce GTX 1080 Ti and NVIDIA GeForce RTX 2080 Ti Founders Edition?
- Stable Diffusion XL: NVIDIA GeForce RTX 2080 Ti Founders Edition leads by roughly 149% (1.68 vs 4.18 images/min) in our testing.
GeForce GTX 1080 Ti full review · NVIDIA GeForce RTX 2080 Ti Founders Edition full review · All AI & Machine Learning rankings