can-i-run-this-llm

GPU comparison

MacBook Air/Pro M5 (32GB) vs NVIDIA RTX 3090 (24GB) for local LLMs

How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 34 tracked models each one can run.

MacBook Air/Pro M5 (32GB)NVIDIA RTX 3090 (24GB)
Memory32.0 GB24.0 GB
Bandwidth153 GB/s936 GB/s
Price (approx)$1,499$1,099
LLMs it runs25 of 3425 of 34
Best model it runsGemma 4 31B · 6–9 tok/sGemma 4 31B · 39–58 tok/s

Both run the same number of models, but the MacBook Air/Pro M5 (32GB) has more memory (32.0 GB), so it can hold larger models at higher quality. The NVIDIA RTX 3090 (24GB) has more memory bandwidth (936 GB/s), so it generates tokens faster at the same model and quant.

What the MacBook Air/Pro M5 (32GB) runs →What the NVIDIA RTX 3090 (24GB) runs →Open the calculator →