Head to head

RTX 5080 vs RTX 3060 12GB

The RTX 5080 holds more — 16 GB against 12 GB — which decides what you can load at all. The RTX 5080 has more bandwidth at 960 GB/s, which decides how fast tokens come out once a model fits.

Model (Q4_K_M, 8K)RTX 5080tok/sRTX 3060 12GBtok/s
Llama 3.1 8B Runs comfortably 121 Runs comfortably 43.7
Llama 3.1 70B Won't fit 1.35 Won't fit 1.13
Llama 3.2 3B Runs comfortably 266 Runs comfortably 97.2
Llama 3.2 1B Runs comfortably 700 Runs comfortably 260
Llama 4 Scout 109B-A17B Won't fit 4.91 Won't fit 4.27
Qwen3 8B Runs comfortably 117 Runs comfortably 42.3
Qwen3 14B Runs comfortably 68.7 Won't fit 22.1
Qwen3 32B Won't fit 4.98 Won't fit 3.06
Qwen3 4B Runs comfortably 212 Runs comfortably 77.4
Qwen3 30B-A3B Won't fit 46.2 Won't fit 26.1
Qwen3 235B-A22B Won't fit 3.36 Won't fit 3.07
Qwen2.5-Coder 32B Won't fit 4.98 Won't fit 3.06
Qwen2.5 7B Runs comfortably 135 Runs comfortably 48.5
Qwen2.5 72B Won't fit 1.31 Won't fit 1.08
Gemma 3 4B Runs comfortably 226 Runs comfortably 82.6
Gemma 3 12B Runs comfortably 82.3 Runs comfortably 29.7

Specifications

RTX 5080RTX 3060 12GB
Memory16 GB12 GB
Bandwidth960 GB/s360 GB/s
FP16 compute112 TFLOPS25 TFLOPS
Launch price$999$329
ArchitectureBlackwellAmpere