

Dead heat, NVIDIA GeForce RTX 3080 and NVIDIA GeForce RTX 4060 Ti 16GB split our benchmark suite evenly.
Both cards were measured first-party on our bench, same suite, same test rig.
The gap is widest in Llama 3.1 8B, where NVIDIA GeForce RTX 3080 leads by 120% (125.85 vs 57.09 tok/s); the closest fight is Stable Diffusion XL (4% apart); VRAM decides part of this one: NVIDIA GeForce RTX 4060 Ti 16GB runs 6 of our 12 AI workloads while the other card runs 3, models that don't fit score zero.
| Benchmark | NVIDIA GeForce RTX 3080 | NVIDIA GeForce RTX 4060 Ti 16GB | Difference |
|---|---|---|---|
| Qwen3 4B tok/s | 184.08 | 96.29 | +91% |
| Llama 3.1 8B tok/s | 125.85 | 57.09 | +120% |
| Qwen2.5-Coder 14B tok/s | 0 | 31.12 | 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 | 4.76 | 4.58 | +4% |
| Z-Image Turbo images/min | 0 | 1.35 | n/a |
| FLUX.1 dev images/min | 0 | 0 | n/a |
| FLUX.1 Kontext dev images/min | 0 | 0 | n/a |
| Qwen-Image-Edit images/min | 0 | 0 | n/a |
| LTX-Video (distilled) frames/s | 0 | 1.5 | n/a |
| Wan 2.2 5B (720p) frames/s | 0 | 0 | n/a |
| NVIDIA GeForce RTX 3080 | NVIDIA GeForce RTX 4060 Ti 16GB | |
|---|---|---|
| VRAM | 10GB | 16GB |
| Transistors | 28,300M | 22,900M |
| Die size | 628.4 mm² | 187.8 mm² |
| Transistor density | 45 M/mm² | 121.9 M/mm² |
| Architecture | Ampere (GA102) | Ada Lovelace |
| Memory bandwidth | 760 GB/s | 288 GB/s |
| Boost clock | 1,710 MHz | 2,535 MHz |
| TDP | 320 W | 165 W |
| Launch MSRP | $699 | $499 |
| Release | 2020-09-17 | 2023-07-18 |
NVIDIA GeForce RTX 3080 full review · NVIDIA GeForce RTX 4060 Ti 16GB full review · All AI & Machine Learning rankings