GPU comparison
MacBook Pro M4 Pro (48GB) vs NVIDIA RTX 3090 (24GB) 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.
| MacBook Pro M4 Pro (48GB) | NVIDIA RTX 3090 (24GB) | |
|---|---|---|
| Memory | 48.0 GB | 24.0 GB |
| Bandwidth | 273 GB/s | 936 GB/s |
| Price (approx) | $2,399 | $899 |
| LLMs it runs | 16 of 22 | 16 of 22 |
| Best model it runs | Gemma 4 31B · 9–13 tok/s | Gemma 4 31B · 31–47 tok/s |
Both run the same number of models, but the MacBook Pro M4 Pro (48GB) has more memory (48.0 GB), so it can hold larger models at higher quality. The NVIDIA RTX 3090 (24GB) has more memory bandwidth (936 GB/s), so it generates tokens faster at the same model and quant.