can-i-run-this-llm

GPU comparison

MacBook Pro M4 Max (128GB) vs NVIDIA RTX 4090 (24GB) for local LLMs

How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 48 tracked models each one can run.

MacBook Pro M4 Max (128GB)NVIDIA RTX 4090 (24GB)
Memory128.0 GB24.0 GB
Bandwidth546 GB/s1008 GB/s
Price (approx)$4,699$2,999
LLMs it runs41 of 4834 of 48
Best model it runsGemma 4 31B · 13–19 tok/sGemma 4 31B · 41–62 tok/s

The MacBook Pro M4 Max (128GB) runs 7 more of the tracked models (41 vs 34), thanks to its 128.0 GB of memory. The NVIDIA RTX 4090 (24GB) has more memory bandwidth (1008 GB/s), so it generates tokens faster at the same model and quant.

What the MacBook Pro M4 Max (128GB) runs →What the NVIDIA RTX 4090 (24GB) runs →Open the calculator →