can-i-run-this-llm

GPU comparison

Mac Studio M2 Ultra (192GB) vs NVIDIA RTX Pro 6000 Blackwell (96GB) for local LLMs

How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 22 tracked models each one can run.

Mac Studio M2 Ultra (192GB)NVIDIA RTX Pro 6000 Blackwell (96GB)
Memory192.0 GB96.0 GB
Bandwidth800 GB/s1792 GB/s
Price (approx)$5,599$8,999
LLMs it runs20 of 2218 of 22
Best model it runsHunyuan Hy3 (MoE) · 48–71 tok/sGemma 4 31B · 18–28 tok/s

The Mac Studio M2 Ultra (192GB) runs 2 more of the tracked models (20 vs 18), thanks to its 192.0 GB of memory. The NVIDIA RTX Pro 6000 Blackwell (96GB) has more memory bandwidth (1792 GB/s), so it generates tokens faster at the same model and quant.

What the Mac Studio M2 Ultra (192GB) runs →What the NVIDIA RTX Pro 6000 Blackwell (96GB) runs →Open the calculator →