

NVIDIA GeForce RTX 3060 wins 4 of 12 benchmarks, averaging 16.2% faster.
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 3060 leads by 25% (65.36 vs 52.4 tok/s); the closest fight is Stable Diffusion XL (6% apart); VRAM decides part of this one: NVIDIA GeForce RTX 3060 runs 4 of our 12 AI workloads while the other card runs 3, models that don't fit score zero.
| Benchmark | NVIDIA GeForce RTX 3060 | GeForce RTX 4060 | Difference |
|---|---|---|---|
| Qwen3 4B tok/s | 102.04 | 86.38 | +18% |
| Llama 3.1 8B tok/s | 65.36 | 52.4 | +25% |
| Qwen2.5-Coder 14B tok/s | 35.52 | 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 | 2.94 | 2.78 | +6% |
| Z-Image Turbo images/min | 0 | 0 | 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 | 0 | n/a |
| Wan 2.2 5B (720p) frames/s | 0 | 0 | n/a |
| NVIDIA GeForce RTX 3060 | GeForce RTX 4060 | |
|---|---|---|
| VRAM | 12GB | 8GB |
| Transistors | 12,000M | 18,900M |
| Die size | 276 mm² | 158.7 mm² |
| Transistor density | 43.5 M/mm² | 119.1 M/mm² |
| Architecture | Ampere (GA106) | Ada Lovelace |
| Memory bandwidth | 360 GB/s | 272 GB/s |
| Boost clock | 1,777 MHz | 2,475 MHz |
| TDP | 170 W | 115 W |
| Launch MSRP | $329 | $299 |
| Release | 2021-02-25 | 2023-05-24 |
NVIDIA GeForce RTX 3060 full review · GeForce RTX 4060 full review · All AI & Machine Learning rankings