can-i-run-this-llm

GPU comparison

Mac Studio M2 Ultra (64GB) vs NVIDIA RTX 4080 (16GB) 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.

Mac Studio M2 Ultra (64GB)NVIDIA RTX 4080 (16GB)
Memory64.0 GB16.0 GB
Bandwidth800 GB/s717 GB/s
Price (approx)$3,999$999
LLMs it runs16 of 1812 of 18
Best model it runsGemma 4 31B · 15–23 tok/sGemma 4 26B-A4B (MoE) · 107–161 tok/s

The Mac Studio M2 Ultra (64GB) runs 4 more of the tracked models (16 vs 12), thanks to its 64.0 GB of memory. The Mac Studio M2 Ultra (64GB) has more memory bandwidth (800 GB/s), so it generates tokens faster at the same model and quant.

What the Mac Studio M2 Ultra (64GB) runs →What the NVIDIA RTX 4080 (16GB) runs →Open the calculator →