llamaperf

A100 40GB vs RTX 3060 12GB

For running local LLMs · 5 reports across 2 models

Side A
A100 40GB
Vendor
nvidia
VRAM
40GB
Memory
Discrete
Side B
RTX 3060 12GB
Vendor
nvidia
VRAM
12GB
Memory
Discrete

Tokens per second by model

ModelA100 40GBRTX 3060 12GB
Qwen3.6up to 35B70.0n=3
Gemma 4up to 31B60.0n=2

More comparisons