can-i-run-this-llm

GPU comparison

MacBook Pro M5 Pro (24GB) vs AMD RX 9070 (16GB) 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)AMD RX 9070 (16GB)
Memory24.0 GB16.0 GB
Bandwidth307 GB/s645 GB/s
Price (approx)$2,199$569
LLMs it runs21 of 3418 of 34
Best model it runsGemma 4 31B · 12–18 tok/sGemma 4 26B-A4B (MoE) · 132–198 tok/s

The MacBook Pro M5 Pro (24GB) runs 3 more of the tracked models (21 vs 18), thanks to its 24.0 GB of memory. The AMD RX 9070 (16GB) has more memory bandwidth (645 GB/s), so it generates tokens faster at the same model and quant.

What the MacBook Pro M5 Pro (24GB) runs →What the AMD RX 9070 (16GB) runs →Open the calculator →