can-i-run-this-llm

GPU comparison

MacBook Pro M5 Pro (64GB) 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 48 tracked models each one can run.

MacBook Pro M5 Pro (64GB)AMD RX 9070 (16GB)
Memory64.0 GB16.0 GB
Bandwidth307 GB/s645 GB/s
Price (approx)$3,399$569
LLMs it runs37 of 4827 of 48
Best model it runsGemma 4 31B · 12–18 tok/sGemma 4 26B-A4B (MoE) · 132–198 tok/s

The MacBook Pro M5 Pro (64GB) runs 10 more of the tracked models (37 vs 27), thanks to its 64.0 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 (64GB) runs →What the AMD RX 9070 (16GB) runs →Open the calculator →