can-i-run-this-llm

GPU comparison

MacBook Air/Pro M5 (16GB) 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 (16GB)NVIDIA RTX 3090 (24GB)
Memory16.0 GB24.0 GB
Bandwidth153 GB/s936 GB/s
Price (approx)$1,099$1,099
LLMs it runs13 of 3425 of 34
Best model it runsDevstral Small 2 24B · 10–15 tok/sGemma 4 31B · 39–58 tok/s

The NVIDIA RTX 3090 (24GB) runs 12 more of the tracked models (25 vs 13), thanks to its 24.0 GB of memory. 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 (16GB) runs →What the NVIDIA RTX 3090 (24GB) runs →Open the calculator →