NVIDIA GeForce GTX 1660 Super vs GeForce RTX 4060, AI & Machine Learning Comparison
GeForce RTX 4060 wins 6 of 21 benchmarks, averaging 8.2% 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 GeForce RTX 4060 leads by 9% (47.17 vs 51.31 tok/s); the closest fight is Llama-3.1-8B (8% apart); VRAM decides part of this one: GeForce RTX 4060 runs 15 of our 12 AI workloads while the other card runs 7, models that don't fit score zero.
Benchmark results head-to-head
| Benchmark | NVIDIA GeForce GTX 1660 Super | GeForce RTX 4060 | Difference |
|---|---|---|---|
| Qwen3-4B tok/s | 79.86 | 86.38 | -8% |
| Llama-3.1-8B tok/s | 48.64 | 52.4 | -7% |
| Qwen3 8B tok/s | 47.17 | 51.31 | -8% |
| Nemotron Nano 9B v2 tok/s | 0 | 37.02 | n/a |
| Gemma 4 12B tok/s | 0 | 33.27 | 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 | 0 | 2.78 | 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 1660 Super | $0.058 |
| GeForce RTX 4060 | $0.078 |
NVIDIA GeForce GTX 1660 Super is 1.34x cheaper per hour. Cheapest on-demand rate we see across RunPod and Vast.
Specifications compared
| NVIDIA GeForce GTX 1660 Super | GeForce RTX 4060 | |
|---|---|---|
| VRAM | 6GB | 8GB |
| Transistors | 6,600M | 18,900M |
| Die size | 284 mm² | 158.7 mm² |
| Process node | 12 nm | 4 nm |
| Transistor density | 23.2 M/mm² | 119.1 M/mm² |
| Architecture | Turing (TU116) | Ada Lovelace |
| Memory bandwidth | 336 GB/s | 272 GB/s |
| Boost clock | 1,785 MHz | 2,475 MHz |
| TDP | 125 W | 115 W |
| Launch MSRP | $229 | $299 |
| Release | 2019-10-29 | 2023-05-24 |
FAQ
- Which is better for ai & machine learning: NVIDIA GeForce GTX 1660 Super or GeForce RTX 4060?
- GeForce RTX 4060 performs better for ai & machine learning, winning 6 of 21 benchmarks in our suite with an average 8.2% advantage.
- What are the main hardware differences between NVIDIA GeForce GTX 1660 Super and GeForce RTX 4060?
- NVIDIA GeForce GTX 1660 Super has 6GB VRAM and a 125W TDP, while GeForce RTX 4060 has 8GB VRAM and a 115W TDP.
- Does VRAM matter more than speed between NVIDIA GeForce GTX 1660 Super and GeForce RTX 4060?
- For AI, yes, GeForce RTX 4060 fits 4 more of our 12 workloads than NVIDIA GeForce GTX 1660 Super. 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 1660 Super and GeForce RTX 4060?
- Qwen3 8B: GeForce RTX 4060 leads by roughly 9% (47.17 vs 51.31 tok/s) in our testing.
NVIDIA GeForce GTX 1660 Super full review · GeForce RTX 4060 full review · All AI & Machine Learning rankings