GPU comparison
Mac Studio M3 Ultra (96GB) vs NVIDIA RTX 6000 Ada (48GB) 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 6000 Ada (48GB) | |
|---|---|---|
| Memory | 96.0 GB | 48.0 GB |
| Bandwidth | 819 GB/s | 960 GB/s |
| Price (approx) | $5,299 | $6,800 |
| LLMs it runs | 30 of 34 | 26 of 34 |
| Best model it runs | Gemma 4 31B · 15–22 tok/s | Gemma 4 31B · 20–30 tok/s |
The Mac Studio M3 Ultra (96GB) runs 4 more of the tracked models (30 vs 26), thanks to its 96.0 GB of memory. The NVIDIA RTX 6000 Ada (48GB) has more memory bandwidth (960 GB/s), so it generates tokens faster at the same model and quant.