Hardware comparison
MacBook Air/Pro M5 (24GB) vs Mac mini M6 (32GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 69 tracked models each one can run.
Scroll sideways to compare both machines. Keyboard: focus the table, then use the arrow keys. Metric names stay visible.
| Hardware | MacBook Air/Pro M5 (24GB) | Mac mini M6 (32GB) |
|---|---|---|
| Memory | 24.0 GB | 32.0 GB (better for this comparison) |
| Bandwidth | 153 GB/s | 170 GB/s (better for this comparison) |
| Price (approx) | $1,299Complete system | $1,299Complete system |
| LLMs it runs | 49 of 69 | 51 of 69 (better for this comparison) |
| Best model it runs | Gemma 4 31BQ2_K · estimated 8–11 tok/s | Gemma 4 31BQ2_K · estimated 8–13 tok/s |
Both prices cover complete systems. Prices are approximate catalog estimates; check current configurations and prices before buying.
Both estimated speeds use the same model and quant shown above. Estimates use 4,096 context tokens, llama.cpp and one stream.
The Mac mini M6 (32GB) runs 2 more of the tracked models (51 vs 49), thanks to its 32.0 GB of memory. The Mac mini M6 (32GB) has more memory bandwidth (170 GB/s). Higher bandwidth can help generation speed, but model, quant, architecture and runtime also affect the estimates.