can-i-run-this-llm

GPU comparison

Mac Studio M3 Ultra (96GB) vs NVIDIA RTX 5080 (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.

Mac Studio M3 Ultra (96GB)NVIDIA RTX 5080 (16GB)
Memory96.0 GB16.0 GB
Bandwidth819 GB/s960 GB/s
Price (approx)$5,299$1,399
LLMs it runs30 of 3418 of 34
Best model it runsGemma 4 31B · 15–22 tok/sGemma 4 26B-A4B (MoE) · 167–251 tok/s

The Mac Studio M3 Ultra (96GB) runs 12 more of the tracked models (30 vs 18), thanks to its 96.0 GB of memory. The NVIDIA RTX 5080 (16GB) has more memory bandwidth (960 GB/s), so it generates tokens faster at the same model and quant.

What the Mac Studio M3 Ultra (96GB) runs →What the NVIDIA RTX 5080 (16GB) runs →Open the calculator →