GPU comparison
MacBook Pro M4 Pro (24GB) 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 48 tracked models each one can run.
| MacBook Pro M4 Pro (24GB) | NVIDIA RTX 3090 (24GB) | |
|---|---|---|
| Memory | 24.0 GB | 24.0 GB |
| Bandwidth | 273 GB/s | 936 GB/s |
| Price (approx) | $1,999 | $1,099 |
| LLMs it runs | 29 of 48 | 34 of 48 |
| Best model it runs | Gemma 4 31B · 11–16 tok/s | Gemma 4 31B · 39–58 tok/s |
The NVIDIA RTX 3090 (24GB) runs 5 more of the tracked models (34 vs 29). With the same nominal memory, more of it is usable for model weights on this architecture. The NVIDIA RTX 3090 (24GB) has more memory bandwidth (936 GB/s), so it generates tokens faster at the same model and quant.