can-i-run-this-llm

GPU comparison

MacBook Pro M5 Pro (64GB) 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 Pro M5 Pro (64GB)NVIDIA RTX 3090 (24GB)
Memory64.0 GB24.0 GB
Bandwidth307 GB/s936 GB/s
Price (approx)$3,399$1,099
LLMs it runs26 of 3425 of 34
Best model it runsGemma 4 31B · 12–18 tok/sGemma 4 31B · 39–58 tok/s

The MacBook Pro M5 Pro (64GB) runs 1 more of the tracked models (26 vs 25), thanks to its 64.0 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 Pro M5 Pro (64GB) runs →What the NVIDIA RTX 3090 (24GB) runs →Open the calculator →