Compare
Compare local AI hardware with workload-aware output.
Operating mode: Balanced. Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
MacBook Pro M2 Pro 16GB wins for coding in balanced mode
Based on model fit, speed, and quality across top recommendations.
MacBook Pro M2 Pro 16GB
WinnerSQwen 3.5 9B
llama.cppQ4_K_MTight fit
10.3 GB / 11.5 GB
27.4 tok/s25K ctx
AGemma 4 E4B
llama.cppQ4_K_MRuns well
8.8 GB / 11.5 GB
23.4 tok/s50K ctx
ACodeGeeX 4 9B
llama.cppQ4_K_MRuns well
8.7 GB / 11.5 GB
27.9 tok/s89K ctx
MacBook Air M2 16GB
SQwen 3.5 9B
llama.cppQ4_K_MTight fit
10.3 GB / 11.5 GB
12.7 tok/s25K ctx
AGemma 4 E4B
llama.cppQ4_K_MRuns well
8.8 GB / 11.5 GB
10.9 tok/s50K ctx
ACodeGeeX 4 9B
llama.cppQ4_K_MRuns well
8.7 GB / 11.5 GB
12.9 tok/s89K ctx
Quick comparison
| Metric | MacBook Pro M2 Pro 16GB | MacBook Air M2 16GB |
|---|---|---|
| Models that fit | 3 | 3 |
| Avg decode tok/s | 26.2 | 12.2 |
| Best grade score | 92 | 89 |