GPU comparison
MacBook Pro M5 Max (36GB) vs MacBook Pro M5 Max (128GB) 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 (36GB) | MacBook Pro M5 Max (128GB) | |
|---|---|---|
| Memory | 36.0 GB | 128.0 GB |
| Bandwidth | 460 GB/s | 614 GB/s |
| Price (approx) | $3,599 | $5,099 |
| LLMs it runs | 47 of 64 | 57 of 64 |
| Best model it runs | Qwen3.8 27B · 13–20 tok/s | Qwen3.8 Flash Next (MoE) · 79–118 tok/s |
The MacBook Pro M5 Max (128GB) runs 10 more of the tracked models (57 vs 47), 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.