can-i-run-this-llm

GPU comparison

MacBook Pro M5 Pro (24GB) 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 (24GB)NVIDIA RTX 3090 (24GB)
Memory24.0 GB24.0 GB
Bandwidth307 GB/s936 GB/s
Price (approx)$2,199$1,099
LLMs it runs21 of 3425 of 34
Best model it runsGemma 4 31B · 12–18 tok/sGemma 4 31B · 39–58 tok/s

The NVIDIA RTX 3090 (24GB) runs 4 more of the tracked models (25 vs 21). With the same nominal memory, more of it is usable for model weights on this architecture. 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 (24GB) runs →What the NVIDIA RTX 3090 (24GB) runs →Open the calculator →