NVIDIA GeForce GTX 1080 vs NVIDIA GeForce GTX 1660 Ti, AI & Machine Learning Comparison
NVIDIA GeForce GTX 1660 Ti wins 3 of 20 benchmarks, averaging 37% 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 Qwen3 8B, where NVIDIA GeForce GTX 1660 Ti leads by 38% (34.97 vs 48.18 tok/s); the closest fight is Qwen3-4B (36% apart); VRAM decides part of this one: NVIDIA GeForce GTX 1080 runs 5 of our 12 AI workloads while the other card runs 3, models that don't fit score zero.
Benchmark results head-to-head
| Benchmark | NVIDIA GeForce GTX 1080 | NVIDIA GeForce GTX 1660 Ti | Difference |
|---|---|---|---|
| Qwen3-4B tok/s | 59.12 | 80.55 | -27% |
| Llama-3.1-8B tok/s | 35.98 | 49.29 | -27% |
| Qwen3 8B tok/s | 34.97 | 48.18 | -27% |
| Gemma 4 12B tok/s | 22.65 | 0 | n/a |
| Qwen2.5-Coder 14B tok/s | 0 | 0 | n/a |
| Qwen3 14B tok/s | 0 | 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 |
| Sana 1.6B images/min | 0 | 0 | n/a |
| Stable Diffusion XL images/min | 1.08 | 0 | n/a |
| 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 |
|---|---|
| NVIDIA GeForce GTX 1080 | $0.049 |
| NVIDIA GeForce GTX 1660 Ti | $0.082 |
NVIDIA GeForce GTX 1080 is 1.67x cheaper per hour. Cheapest on-demand rate we see across RunPod and Vast.
Specifications compared
| NVIDIA GeForce GTX 1080 | NVIDIA GeForce GTX 1660 Ti | |
|---|---|---|
| VRAM | 8GB | 6GB |
| Transistors | 7,200M | 6,600M |
| Die size | 314 mm² | 284 mm² |
| Process node | 16 nm | 12 nm |
| Transistor density | 22.9 M/mm² | 23.2 M/mm² |
| Architecture | Pascal | Turing (TU116) |
| Memory bandwidth | 320 GB/s | 288 GB/s |
| Boost clock | 1,733 MHz | 1,770 MHz |
| TDP | 180 W | 120 W |
| Launch MSRP | $599 | $279 |
| Release | 2016-05-27 | 2019-02-22 |
FAQ
- Which is better for ai & machine learning: NVIDIA GeForce GTX 1080 or NVIDIA GeForce GTX 1660 Ti?
- NVIDIA GeForce GTX 1660 Ti performs better for ai & machine learning, winning 3 of 20 benchmarks in our suite with an average 37% advantage.
- What are the main hardware differences between NVIDIA GeForce GTX 1080 and NVIDIA GeForce GTX 1660 Ti?
- NVIDIA GeForce GTX 1080 has 8GB VRAM and a 180W TDP, while NVIDIA GeForce GTX 1660 Ti has 6GB VRAM and a 120W TDP.
- Does VRAM matter more than speed between NVIDIA GeForce GTX 1080 and NVIDIA GeForce GTX 1660 Ti?
- For AI, yes, NVIDIA GeForce GTX 1080 fits 4 more of our 12 workloads than NVIDIA GeForce GTX 1660 Ti. 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 NVIDIA GeForce GTX 1080 and NVIDIA GeForce GTX 1660 Ti?
- Qwen3 8B: NVIDIA GeForce GTX 1660 Ti leads by roughly 38% (34.97 vs 48.18 tok/s) in our testing.
NVIDIA GeForce GTX 1080 full review · NVIDIA GeForce GTX 1660 Ti full review · All AI & Machine Learning rankings