GPU comparison
MacBook Pro M5 Pro (24GB) vs NVIDIA RTX 5070 (12GB) 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.
| MacBook Pro M5 Pro (24GB) | NVIDIA RTX 5070 (12GB) | |
|---|---|---|
| Memory | 24.0 GB | 12.0 GB |
| Bandwidth | 307 GB/s | 672 GB/s |
| Price (approx) | $2,199 | $629 |
| LLMs it runs | 21 of 34 | 13 of 34 |
| Best model it runs | Gemma 4 31B · 12–18 tok/s | Devstral Small 2 24B · 45–68 tok/s |
The MacBook Pro M5 Pro (24GB) runs 8 more of the tracked models (21 vs 13), thanks to its 24.0 GB of memory. The NVIDIA RTX 5070 (12GB) has more memory bandwidth (672 GB/s), so it generates tokens faster at the same model and quant.