can-i-run-this-llm

GPU comparison

MacBook Pro M4 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 18 tracked models each one can run.

MacBook Pro M4 Pro (24GB)NVIDIA RTX 3090 (24GB)
Memory24.0 GB24.0 GB
Bandwidth273 GB/s936 GB/s
Price (approx)$1,999$800
LLMs it runs13 of 1815 of 18
Best model it runsGemma 4 26B-A4B (MoE) · 40–61 tok/sGemma 4 31B · 31–47 tok/s

The NVIDIA RTX 3090 (24GB) runs 2 more of the tracked models (15 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 Pro M4 Pro (24GB) runs →What the NVIDIA RTX 3090 (24GB) runs →Open the calculator →