GPU comparison
MacBook Pro M5 Max (128GB) 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 Max (128GB) | NVIDIA RTX 3060 (12GB) | |
|---|---|---|
| Memory | 128.0 GB | 12.0 GB |
| Bandwidth | 614 GB/s | 360 GB/s |
| Price (approx) | $5,099 | $329 |
| LLMs it runs | 57 of 64 | 27 of 64 |
| Best model it runs | Qwen3.8 Flash Next (MoE) · 79–118 tok/s | Devstral Small 2 24B · 26–39 tok/s |
The MacBook Pro M5 Max (128GB) runs 30 more of the tracked models (57 vs 27), thanks to its 128.0 GB of memory. The MacBook Pro M5 Max (128GB) has more memory bandwidth (614 GB/s), so it generates tokens faster at the same model and quant.