GPU comparison
Mac Studio M3 Ultra (96GB) vs NVIDIA DGX Spark (GB10, 128GB) 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 DGX Spark (GB10, 128GB) | |
|---|---|---|
| Memory | 96.0 GB | 128.0 GB |
| Bandwidth | 819 GB/s | 273 GB/s |
| Price (approx) | $5,299 | $4,699 |
| LLMs it runs | 30 of 34 | 30 of 34 |
| Best model it runs | Gemma 4 31B · 15–22 tok/s | Gemma 4 31B · 11–16 tok/s |
Both run the same number of models, but the NVIDIA DGX Spark (GB10, 128GB) has more memory (128.0 GB), so it can hold larger models at higher quality. The Mac Studio M3 Ultra (96GB) has more memory bandwidth (819 GB/s), so it generates tokens faster at the same model and quant.