GPU comparison
MacBook Pro M5 Max (36GB) vs Intel Arc B580 (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 (36GB) | Intel Arc B580 (12GB) | |
|---|---|---|
| Memory | 36.0 GB | 12.0 GB |
| Bandwidth | 460 GB/s | 456 GB/s |
| Price (approx) | $3,599 | $289 |
| LLMs it runs | 47 of 64 | 27 of 64 |
| Best model it runs | Qwen3.8 27B · 13–20 tok/s | Devstral Small 2 24B · 32–48 tok/s |
The MacBook Pro M5 Max (36GB) runs 20 more of the tracked models (47 vs 27), thanks to its 36.0 GB of memory. The MacBook Pro M5 Max (36GB) has more memory bandwidth (460 GB/s), so it generates tokens faster at the same model and quant.