GPU comparison
Mac Studio M2 Ultra (64GB) 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 18 tracked models each one can run.
| Mac Studio M2 Ultra (64GB) | NVIDIA RTX Pro 6000 Blackwell (96GB) | |
|---|---|---|
| Memory | 64.0 GB | 96.0 GB |
| Bandwidth | 800 GB/s | 1792 GB/s |
| Price (approx) | $3,999 | $8,500 |
| LLMs it runs | 16 of 18 | 16 of 18 |
| Best model it runs | Gemma 4 31B · 15–23 tok/s | Gemma 4 31B · 18–28 tok/s |
Both run the same number of models, but the NVIDIA RTX Pro 6000 Blackwell (96GB) has more memory (96.0 GB), so it can hold larger models at higher quality. 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.