Head to head

RTX 3090 vs RTX 3060 12GB

The RTX 3090 holds more — 24 GB against 12 GB — which decides what you can load at all. The RTX 3090 has more bandwidth at 936 GB/s, which decides how fast tokens come out once a model fits.

Model (Q4_K_M, 8K)RTX 3090tok/sRTX 3060 12GBtok/s
Llama 3.1 8B Runs comfortably 112 Runs comfortably 43.7
Llama 3.1 70B Won't fit 1.67 Won't fit 1.13
Llama 3.2 3B Runs comfortably 246 Runs comfortably 97.2
Llama 3.2 1B Runs comfortably 650 Runs comfortably 260
Llama 4 Scout 109B-A17B Won't fit 5.39 Won't fit 4.27
Qwen3 8B Runs comfortably 108 Runs comfortably 42.3
Qwen3 14B Runs comfortably 63.5 Won't fit 22.1
Qwen3 32B Fits, but tight 29.5 Won't fit 3.06
Qwen3 4B Runs comfortably 196 Runs comfortably 77.4
Qwen3 30B-A3B Runs comfortably 117 Won't fit 26.1
Qwen3 235B-A22B Won't fit 3.36 Won't fit 3.07
Qwen2.5-Coder 32B Fits, but tight 29.5 Won't fit 3.06
Qwen2.5 7B Runs comfortably 125 Runs comfortably 48.5
Qwen2.5 72B Won't fit 1.59 Won't fit 1.08
Gemma 3 4B Runs comfortably 209 Runs comfortably 82.6
Gemma 3 12B Runs comfortably 76.1 Runs comfortably 29.7

Specifications

RTX 3090RTX 3060 12GB
Memory24 GB12 GB
Bandwidth936 GB/s360 GB/s
FP16 compute71 TFLOPS25 TFLOPS
Launch price$1,499$329
ArchitectureAmpereAmpere