llamaperf

RTX 3060 12GB vs RTX 5080

For running local LLMs · 6 reports across 2 models

Side A
RTX 3060 12GB
Vendor
nvidia
VRAM
12GB
Memory
Discrete
Side B
RTX 5080
Vendor
nvidia
VRAM
16GB
Memory
Discrete

Tokens per second by model

ModelRTX 3060 12GBRTX 5080
Qwen3.6up to 35B70.0n=356.0n=1
Gemma 4up to 31B60.0n=2

More comparisons