GPU comparison
MacBook Pro M5 Pro (24GB) vs NVIDIA RTX 3060 (12GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 64 tracked models each one can run.
| MacBook Pro M5 Pro (24GB) | NVIDIA RTX 3060 (12GB) | |
|---|---|---|
| Memory | 24.0 GB | 12.0 GB |
| Bandwidth | 307 GB/s | 360 GB/s |
| Price (approx) | $2,199 | $329 |
| LLMs it runs | 45 of 64 | 27 of 64 |
| Best model it runs | Qwen3.8 27B · 14–21 tok/s | Devstral Small 2 24B · 26–39 tok/s |
The MacBook Pro M5 Pro (24GB) runs 18 more of the tracked models (45 vs 27), thanks to its 24.0 GB of memory. The NVIDIA RTX 3060 (12GB) has more memory bandwidth (360 GB/s), so it generates tokens faster at the same model and quant.